aerospaceboy
ebe33392ca
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.
197 lines
12 KiB
Python
197 lines
12 KiB
Python
from html import escape
|
||
from pathlib import Path
|
||
|
||
from openpyxl import Workbook
|
||
from openpyxl.styles import Font, PatternFill
|
||
from sqlalchemy import select
|
||
|
||
from .config import get_settings
|
||
from .evidence import POLICY_VERSION
|
||
from .knowledge_pages import evidence_links
|
||
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.
|
||
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,
|
||
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):
|
||
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) 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 = 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,
|
||
"confidence": score.confidence if score else None,
|
||
"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_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}
|
||
|
||
|
||
def batch_projects(db, batch: ScoringBatch):
|
||
if batch.project_ids is None:
|
||
return db.scalars(select(Project).where(Project.course_version_id == batch.course_version_id).order_by(Project.id)).all()
|
||
if not batch.project_ids:
|
||
return []
|
||
by_id = {project.id: project for project in db.scalars(select(Project).where(Project.id.in_(batch.project_ids))).all()}
|
||
return [by_id[project_id] for project_id in batch.project_ids if project_id in by_id]
|
||
|
||
|
||
def export_excel(db, batch_id: int):
|
||
batch = db.get(ScoringBatch, batch_id)
|
||
if not batch:
|
||
raise ValueError("评分批次不存在")
|
||
root = get_settings().exports_path
|
||
root.mkdir(parents=True, exist_ok=True)
|
||
task = ExportTask(batch_id=batch_id, kind="excel", status="running")
|
||
db.add(task)
|
||
db.flush()
|
||
path = root / f"batch-{batch_id}-scores-{task.id}.xlsx"
|
||
try:
|
||
book = Workbook()
|
||
sheet = book.active
|
||
sheet.title = "成绩"
|
||
final_criteria = [c for c in batch.rubric_snapshot["criteria"] if c["category"] == "final"]
|
||
sheet.append(["学号", "姓名", "选题", "阶段报告1", "阶段报告2", "阶段报告3", *[c["name"] for c in final_criteria], "期末成绩", "总评", "状态", "批次", "规则版本"])
|
||
for project in batch_projects(db, batch):
|
||
result = project_result(db, batch, project)
|
||
scores = {row["criterion"]["criterion_id"]: row["final_score"] for row in result["rows"]}
|
||
totals_ = result["totals"]
|
||
sheet.append([result["student_no"], result["name"], result["topic"], *[totals_[key] for key in ("stage1", "stage2", "stage3")],
|
||
*[scores.get(c["criterion_id"]) for c in final_criteria], totals_["final"], totals_["overall"],
|
||
"完成" if totals_["overall"] is not None else "未完成/待人工处理", batch.id, batch.rubric_version_id])
|
||
sheet.freeze_panes = "D2"
|
||
sheet.auto_filter.ref = sheet.dimensions
|
||
for cell in sheet[1]:
|
||
cell.font = Font(bold=True, color="FFFFFF")
|
||
cell.fill = PatternFill("solid", fgColor="153C65")
|
||
for column in sheet.columns:
|
||
letter = column[0].column_letter
|
||
sheet.column_dimensions[letter].width = min(50, max(12, max(len(str(cell.value or "")) for cell in column) + 2))
|
||
book.save(path)
|
||
task.path, task.status = str(path), "completed"
|
||
except Exception as exc:
|
||
task.status, task.error = "failed", str(exc)[:1000]
|
||
db.commit()
|
||
raise
|
||
db.commit()
|
||
return task
|
||
|
||
|
||
def _html_report(result, batch):
|
||
esc = lambda value: escape("" if value is None else str(value))
|
||
rows = []
|
||
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'}"
|
||
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(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>{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>
|
||
body {{ font-family: 'Noto Sans CJK SC', sans-serif; font-size: 11px; color: #172b4d; }}
|
||
h1 {{ color: #153c65; }} section {{ border-bottom: 1px solid #ccd7e0; break-inside: avoid; }}
|
||
h3 {{ margin-bottom: 3px; }} p {{ margin: 3px 0; }} li {{ margin: 3px 0; }}
|
||
</style><body><h1>WiseGrade 智评 · 学生反馈</h1>
|
||
<p>学号：{esc(result['student_no'])} 姓名：{esc(result['name'])} 选题：{esc(result['topic'])}</p>
|
||
<p>评分批次：{batch.id} 课程版本：{batch.course_version_id} 规则版本：{batch.rubric_version_id}</p>
|
||
<p>模型：{esc(batch.model_config_snapshot.get('model'))} 嵌入模型：{esc(batch.embedding_model_name)} ({esc(batch.embedding_model_version)})</p>
|
||
<h2>成绩</h2><p>阶段1：{esc(totals_['stage1'])} 阶段2：{esc(totals_['stage2'])} 阶段3：{esc(totals_['stage3'])} 期末：{esc(totals_['final'])} 总评：{esc(totals_['overall'])}</p>
|
||
{''.join(rows)}</body></html>"""
|
||
|
||
|
||
def export_project_pdf(db, batch_id: int, project_id: int):
|
||
batch = db.get(ScoringBatch, batch_id)
|
||
project = db.get(Project, project_id)
|
||
if not batch or not project or project.course_version_id != batch.course_version_id or (batch.project_ids is not None and project_id not in batch.project_ids):
|
||
raise ValueError("批次或项目不存在")
|
||
root = get_settings().exports_path
|
||
root.mkdir(parents=True, exist_ok=True)
|
||
task = ExportTask(batch_id=batch_id, project_id=project_id, kind="pdf", status="running")
|
||
db.add(task)
|
||
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:
|
||
task.status, task.error = "failed", str(exc)[:1000]
|
||
db.commit()
|
||
raise
|
||
db.commit()
|
||
return task
|