fix: improve import, evidence indexing and material-scoped grading

Preserve document revisions and evidence, harden indexing and export behavior, add explicit material selection and direct-folder import, validate model JSON schemas with safe error messages, and retain student selection while loading scoring data.

backend/wisegrade/exports.py

@@ -4,11 +4,11 @@ from pathlib import Path
 from openpyxl import Workbook
 from openpyxl.styles import Font, PatternFill
 from sqlalchemy import select
-from weasyprint import HTML
 
 from .config import get_settings
+from .evidence import POLICY_VERSION
 from .knowledge_pages import evidence_links
-from .models import (CriterionScore, ExportTask, Project, ScoreEvidence, ScoringBatch, Student, SubmissionFile)
+from .models import (CriterionScore, ExportTask, KnowledgeDocument, KnowledgePage, Project, ScoreEvidence, ScoringBatch, Student, SubmissionFile)
 from .rules import totals
 
 #: Teacher-facing wording for a criterion status, shared by exports and the API.
@@ -43,6 +43,20 @@ def project_result(db, batch: ScoringBatch, project: Project):
                         CriterionScore.project_id == project.id)).all()
     by_id = {score.criterion_id: score for score in scores}
     criteria = batch.rubric_snapshot["criteria"]
+    all_evidence = db.scalars(select(ScoreEvidence).where(ScoreEvidence.score_id.in_([s.id for s in scores]))).all() if scores else []
+    evidence_by_score = {}
+    for item in all_evidence:
+        evidence_by_score.setdefault(item.score_id, []).append(item)
+    file_ids = {item.submission_file_id for item in all_evidence if item.submission_file_id}
+    file_names = dict(db.execute(select(SubmissionFile.id, SubmissionFile.relative_path).where(SubmissionFile.id.in_(file_ids))).all()) if file_ids else {}
+    # Keep canonical source entities alive for this result, so page_links uses the
+    # session identity map instead of issuing a query for every quotation.
+    doc_ids = {item.document_id for item in all_evidence if item.document_id}
+    documents = db.scalars(select(KnowledgeDocument).where(KnowledgeDocument.id.in_(doc_ids))).all() if doc_ids else []
+    retired_ids = {doc.id for doc in documents if doc.status == "superseded"}
+    cited_pages = {item.page for item in all_evidence}
+    pages = db.scalars(select(KnowledgePage).where(KnowledgePage.document_id.in_(doc_ids),
+                                                KnowledgePage.page.in_(cited_pages))).all() if doc_ids else []
     totals_ = totals({key: score.final_score for key, score in by_id.items()}, criteria, batch.rubric_snapshot["weights"])
     rows = []
     def evidence_dict(item, links):
@@ -53,12 +67,13 @@ def project_result(db, batch: ScoringBatch, project: Project):
                 "source_role": item.source_role or "content",
                 # A quotation saved before the evidence policy existed is labelled as a
                 # historical citation and never presented as report body evidence.
-                "historical": bool(item.historical),
-                "document": db.get(SubmissionFile, item.submission_file_id).relative_path if item.submission_file_id else "课程资料",
-                **links}
+                "historical": bool(item.historical) or item.document_id in retired_ids
+                              or batch.rubric_snapshot.get("evidence_plan", {}).get("version") != POLICY_VERSION,
+                "document": file_names.get(item.submission_file_id, "来源材料") if item.submission_file_id else "课程资料",
+                "url": links["url"], "image_url": links["image_url"]}
     for criterion in criteria:
         score = by_id.get(criterion["criterion_id"])
-        evidence = db.scalars(select(ScoreEvidence).where(ScoreEvidence.score_id == score.id)).all() if score else []
+        evidence = evidence_by_score.get(score.id, []) if score else []
         rows.append({"criterion": criterion, "score_id": score.id if score else None,
                      "model_score": score.model_score if score else None, "teacher_score": score.teacher_score if score else None,
                      "final_score": score.final_score if score else None,
@@ -124,7 +139,7 @@ def export_excel(db, batch_id: int):
 
 
 def _html_report(result, batch):
-    esc = lambda value: escape(str(value or ""))
+    esc = lambda value: escape("" if value is None else str(value))
     rows = []
     for row in result["rows"]:
         criterion = row["criterion"]
@@ -170,6 +185,7 @@ def export_project_pdf(db, batch_id: int, project_id: int):
     db.flush()
     path = root / f"batch-{batch_id}-project-{project_id}-{task.id}.pdf"
     try:
+        from weasyprint import HTML
         HTML(string=_html_report(project_result(db, batch, project), batch)).write_pdf(path)
         task.path, task.status = str(path), "completed"
     except Exception as exc: