feat: separate contents, abstract and body evidence

backend/wisegrade/exports.py

@@ -11,6 +11,32 @@ from .knowledge_pages import evidence_links
 from .models import (CriterionScore, ExportTask, Project, ScoreEvidence, ScoringBatch, Student, SubmissionFile)
 from .rules import totals
 
+#: Teacher-facing wording for a criterion status, shared by exports and the API.
+STATUS_LABELS = {
+    "pending": "待评分",
+    "scored": "模型已评分",
+    "reviewed": "教师已复核",
+    "needs_review": "待教师复核",
+    "unscorable": "材料缺失或解析失败",
+    "failed": "模型调用失败",
+}
+PAGE_TYPE_LABELS = {
+    "cover": "封面", "abstract": "摘要", "toc": "目录", "body": "正文",
+    "appendix": "附录", "references": "参考文献", "unknown": "识别不确定",
+    "mixed": "目录与正文混合页",
+}
+#: Batch status wording. ``review_required`` means grading finished but some criteria
+#: still need a teacher decision, which is not the same as an incomplete batch.
+BATCH_STATUS_LABELS = {
+    "created": "待启动", "queued": "排队中", "running": "运行中",
+    "completed": "已完成", "review_required": "已完成，有待复核项",
+    "partial": "部分完成", "failed": "失败",
+}
+
+
+def page_type_label(value) -> str:
+    return PAGE_TYPE_LABELS.get(str(value or "unknown"), "未分类页面")
+
 
 def project_result(db, batch: ScoringBatch, project: Project):
     scores = db.scalars(select(CriterionScore).where(CriterionScore.batch_id == batch.id,
@@ -19,10 +45,15 @@ def project_result(db, batch: ScoringBatch, project: Project):
     criteria = batch.rubric_snapshot["criteria"]
     totals_ = totals({key: score.final_score for key, score in by_id.items()}, criteria, batch.rubric_snapshot["weights"])
     rows = []
-    def evidence_dict(item):
-        links = evidence_links(db, item)
+    def evidence_dict(item, links):
         return {"page": item.page, "quote": item.quote, "file_id": item.submission_file_id,
                 "document_id": item.document_id,
+                "target_id": item.target_id or "", "target_label": item.target_label or "",
+                "page_type": item.page_type or links.get("page_type") or "unknown",
+                "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}
     for criterion in criteria:
@@ -35,7 +66,8 @@ def project_result(db, batch: ScoringBatch, project: Project):
                      "model_comment": score.model_comment if score else "", "teacher_comment": score.teacher_comment if score else None,
                      "missing_evidence": score.missing_evidence if score else [], "suggestion": score.suggestion if score else "",
                      "status": score.status if score else "pending", "error": score.error if score else "",
-                     "evidence": [evidence_dict(item) for item in evidence]})
+                     "evidence_gaps": (score.evidence_gaps or []) if score else [],
+                     "evidence": [evidence_dict(item, evidence_links(db, item)) for item in evidence]})
     student = db.get(Student, project.student_id)
     return {"project_id": project.id, "student_no": student.student_no, "name": student.name, "topic": project.topic,
             "totals": totals_, "rows": rows, "facts": project.facts}
@@ -97,14 +129,21 @@ def _html_report(result, batch):
     for row in result["rows"]:
         criterion = row["criterion"]
         evidences = "".join(
-            f"<li>{esc(e['document'])} · 第{e['page']}{'张幻灯片' if str(e['document']).lower().endswith('.pptx') else '页'}：{esc(e['quote'])}</li>"
+            f"<li>{esc(e['document'])} · 第{e['page']}{'张幻灯片' if str(e['document']).lower().endswith('.pptx') else '页'}"
+            f"（{esc(page_type_label(e.get('page_type')))}{'，历史评分引用' if e.get('historical') else ''}）"
+            f"{' 支持：' + esc(e['target_label']) if e.get('target_label') else ''}：{esc(e['quote'])}</li>"
             for e in row["evidence"]
         )
         missing = "、".join(row["missing_evidence"] or [])
+        gaps = "；".join(f"{gap.get('target_label')}（检索范围：{'、'.join(page_type_label(t) for t in gap.get('searched_page_types') or []) or '正文'}）"
+                        for gap in row.get("evidence_gaps") or [])
+        review = "本项缺少正文证据，已转教师复核。" if row["status"] == "needs_review" else ""
         rows.append(f"<section><h3>{esc(criterion['name'])}（{esc(row['final_score'])} / {criterion['max_score']}）</h3>"
-                    f"<p>模型原始分：{esc(row['model_score'])}；教师修改分：{esc(row['teacher_score'])}；状态：{esc(row['status'])}</p>"
+                    f"<p>模型原始分：{esc(row['model_score'])}；教师修改分：{esc(row['teacher_score'])}；状态：{esc(STATUS_LABELS.get(row['status'], row['status']))}</p>"
                     f"<p>模型评语：{esc(row['model_comment'])}</p><p>教师评语：{esc(row['teacher_comment'])}</p>"
-                    f"<p>缺失证据：{esc(missing)}</p><p>建议：{esc(row['suggestion'])}</p><p>异常：{esc(row['error'])}</p>"
+                    f"<p>{esc(review)}</p>"
+                    f"<p>缺失证据：{esc(missing)}</p><p>缺正文证据的目标：{esc(gaps)}</p>"
+                    f"<p>建议：{esc(row['suggestion'])}</p><p>异常：{esc(row['error'])}</p>"
                     f"<ul>{evidences}</ul></section>")
     totals_ = result["totals"]
     return f"""<!doctype html><html lang="zh"><meta charset="utf-8"><style>