From 5e8d901a1828179593ee1eb7e27b467d706b52c6 Mon Sep 17 00:00:00 2001 From: sit002 Date: Tue, 2 Dec 2025 15:17:53 +0800 Subject: [PATCH] security: remove .autograde from student repo - Grading scripts are now fetched from tests repo at runtime - Students cannot modify grading scripts to cheat - Workflow fetches scripts from private tests repo --- .autograde/aggregate_final_grade.py | 119 ---- .autograde/aggregate_llm_grades.py | 121 ---- .autograde/create_minimal_metadata.py | 372 ----------- .autograde/generate_pdf_report.py | 815 ----------------------- .autograde/grade.py | 187 ------ .autograde/grade_grouped.py | 207 ------ .autograde/llm_grade.py | 249 ------- .autograde/objective_grade.py | 444 ------------ .autograde/post_comment.py | 155 ----- .autograde/run_tests.py | 164 ----- .autograde/test_objective_grade.sh | 95 --- .autograde/upload_metadata.py | 157 ----- .autograde/workflow_templates/README.md | 216 ------ .autograde/workflow_templates/java.yml | 200 ------ .autograde/workflow_templates/python.yml | 206 ------ .autograde/workflow_templates/r.yml | 200 ------ .gitea/workflows/autograde.yml | 25 +- 17 files changed, 21 insertions(+), 3911 deletions(-) delete mode 100644 .autograde/aggregate_final_grade.py delete mode 100644 .autograde/aggregate_llm_grades.py delete mode 100644 .autograde/create_minimal_metadata.py delete mode 100644 .autograde/generate_pdf_report.py delete mode 100644 .autograde/grade.py delete mode 100644 .autograde/grade_grouped.py delete mode 100644 .autograde/llm_grade.py delete mode 100644 .autograde/objective_grade.py delete mode 100644 .autograde/post_comment.py delete mode 100644 .autograde/run_tests.py delete mode 100644 .autograde/test_objective_grade.sh delete mode 100644 .autograde/upload_metadata.py delete mode 100644 .autograde/workflow_templates/README.md delete mode 100644 .autograde/workflow_templates/java.yml delete mode 100644 .autograde/workflow_templates/python.yml delete mode 100644 .autograde/workflow_templates/r.yml diff --git a/.autograde/aggregate_final_grade.py b/.autograde/aggregate_final_grade.py deleted file mode 100644 index 2f19bd5..0000000 --- a/.autograde/aggregate_final_grade.py +++ /dev/null @@ -1,119 +0,0 @@ -#!/usr/bin/env python3 -""" -期末大作业成绩汇总脚本 - -汇总编程测试分数 + REPORT.md 分数 + FRONTEND.md 分数 -""" - -import argparse -import json -import os -import sys - - -def load_json(filepath, default=None): - """安全加载 JSON 文件""" - if not os.path.exists(filepath): - return default or {} - try: - with open(filepath, "r", encoding="utf-8") as f: - return json.load(f) - except Exception as e: - print(f"Error loading {filepath}: {e}", file=sys.stderr) - return default or {} - - -def main(): - parser = argparse.ArgumentParser(description="Aggregate final project grades") - parser.add_argument("--programming", required=True, help="Programming test grade JSON") - parser.add_argument("--report", required=True, help="REPORT.md LLM grade JSON") - parser.add_argument("--frontend", required=True, help="FRONTEND.md LLM grade JSON") - parser.add_argument("--out", default="final_grade.json", help="Output JSON file") - parser.add_argument("--summary", default="final_summary.md", help="Output summary markdown") - args = parser.parse_args() - - # 加载各部分成绩 - prog_grade = load_json(args.programming, {"total_score": 0, "max_score": 80}) - report_grade = load_json(args.report, {"total": 0}) - frontend_grade = load_json(args.frontend, {"total": 0}) - - # 提取分数 - prog_score = prog_grade.get("total_score", 0) - prog_max = prog_grade.get("max_score", 80) - - report_score = report_grade.get("total", 0) - report_max = 10 # REPORT.md 满分 10 分 - - frontend_score = frontend_grade.get("total", 0) - frontend_max = 10 # FRONTEND.md 满分 10 分 - - # 计算总分 - total_score = prog_score + report_score + frontend_score - total_max = prog_max + report_max + frontend_max - - # 构建最终成绩数据（保留 LLM 评分的详细内容） - final_grade = { - "total_score": round(total_score, 2), - "max_score": total_max, - "breakdown": { - "programming": { - "score": round(prog_score, 2), - "max_score": prog_max, - "groups": prog_grade.get("groups", {}) - }, - "report": { - "score": round(report_score, 2), - "max_score": report_max, - "flags": report_grade.get("flags", []), - "confidence": report_grade.get("confidence"), - "criteria": report_grade.get("criteria", []) # LLM 评分详情 - }, - "frontend": { - "score": round(frontend_score, 2), - "max_score": frontend_max, - "flags": frontend_grade.get("flags", []), - "confidence": frontend_grade.get("confidence"), - "criteria": frontend_grade.get("criteria", []) # LLM 评分详情 - } - } - } - - # 保存 final_grade.json - with open(args.out, "w", encoding="utf-8") as f: - json.dump(final_grade, f, ensure_ascii=False, indent=2) - - # 生成 summary.md - with open(args.summary, "w", encoding="utf-8") as f: - f.write("# 期末大作业成绩报告\n\n") - f.write(f"## 总分：{total_score:.2f} / {total_max}\n\n") - - f.write("## 分项成绩\n\n") - f.write("| 项目 | 得分 | 满分 | 备注 |\n") - f.write("|------|------|------|------|\n") - f.write(f"| 编程测试 | {prog_score:.2f} | {prog_max} | Core + Advanced + Challenge |\n") - f.write(f"| REPORT.md | {report_score:.2f} | {report_max} | 后端与系统设计报告 |\n") - f.write(f"| FRONTEND.md | {frontend_score:.2f} | {frontend_max} | 前端界面与交互设计报告 |\n") - - # 编程测试详情 - if prog_grade.get("groups"): - f.write("\n### 编程测试详情\n\n") - f.write("| 分组 | 通过 | 总数 | 得分 | 满分 |\n") - f.write("|------|------|------|------|------|\n") - for group_name, group_info in prog_grade["groups"].items(): - f.write(f"| {group_name} | {group_info.get('passed', 0)} | " - f"{group_info.get('total', 0)} | {group_info.get('score', 0):.2f} | " - f"{group_info.get('max_score', 0)} |\n") - - # 标记 - all_flags = report_grade.get("flags", []) + frontend_grade.get("flags", []) - if all_flags: - f.write("\n### 标记\n\n") - for flag in set(all_flags): - f.write(f"- {flag}\n") - - print(f"Final grade: {total_score:.2f}/{total_max}") - - -if __name__ == "__main__": - main() - diff --git a/.autograde/aggregate_llm_grades.py b/.autograde/aggregate_llm_grades.py deleted file mode 100644 index 44f2fce..0000000 --- a/.autograde/aggregate_llm_grades.py +++ /dev/null @@ -1,121 +0,0 @@ -#!/usr/bin/env python3 -""" -聚合多个 LLM 评分结果 -""" -import json -import argparse -from pathlib import Path - - -def load_grade(filepath): - """加载单个评分文件""" - try: - with open(filepath, 'r', encoding='utf-8') as f: - return json.load(f) - except FileNotFoundError: - print(f"Warning: {filepath} not found") - return None - except json.JSONDecodeError as e: - print(f"Error parsing {filepath}: {e}") - return None - - -def aggregate_grades(input_files, output_file, summary_file): - """聚合多个评分文件""" - grades = [] - total_score = 0 - max_score = 0 - need_review_count = 0 - - for input_file in input_files: - grade = load_grade(input_file) - if grade: - grades.append(grade) - # 支持两种格式：'total' (llm_grade.py) 或 'score' (旧格式) - score = grade.get('total', grade.get('score', 0)) - total_score += score - # 默认每题 10 分 - max_score += grade.get('max_score', 10) - # 检查是否需要审核 - if 'need_review' in grade.get('flags', []) or grade.get('need_review', False): - need_review_count += 1 - - # 计算总分 - final_score = total_score if max_score > 0 else 0 - final_max_score = max_score - - # 生成汇总结果 - result = { - 'total_score': final_score, - 'max_score': final_max_score, - 'questions': len(grades), - 'need_review': need_review_count > 0, - 'details': grades - } - - # 保存 JSON - with open(output_file, 'w', encoding='utf-8') as f: - json.dump(result, f, indent=2, ensure_ascii=False) - - # 生成 Markdown 摘要 - summary_lines = [ - '# LLM 简答题评分汇总', - '', - f'**总分**: {final_score:.1f} / {final_max_score:.1f}', - f'**题目数**: {len(grades)}', - f'**需要人工审核**: {"是" if result["need_review"] else "否"}', - '', - '## 各题详情', - '' - ] - - for i, grade in enumerate(grades, 1): - q_name = grade.get('question', f'Q{i}') - # 支持两种格式：'total' (llm_grade.py) 或 'score' (旧格式) - score = grade.get('total', grade.get('score', 0)) - max_q_score = grade.get('max_score', 10) - # 检查是否需要审核 - need_review = 'need_review' in grade.get('flags', []) or grade.get('need_review', False) - confidence = grade.get('confidence', 1.0) - - summary_lines.append(f'### SA{i}') - summary_lines.append(f'- **得分**: {score:.2f} / {max_q_score:.1f}') - summary_lines.append(f'- **置信度**: {confidence:.2f}') - if need_review: - summary_lines.append('- ⚠️ **需要人工审核**') - - # 显示分项评分 - if 'criteria' in grade: - summary_lines.append('- **分项**:') - for criterion in grade['criteria']: - crit_id = criterion.get('id', '') - crit_score = criterion.get('score', 0) - crit_reason = criterion.get('reason', '') - summary_lines.append(f' - {crit_id}: {crit_score:.1f} - {crit_reason}') - - summary_lines.append('') - - with open(summary_file, 'w', encoding='utf-8') as f: - f.write('\n'.join(summary_lines)) - - print(f"✅ Aggregated {len(grades)} grades") - print(f" Total: {final_score:.1f} / {final_max_score:.1f}") - print(f" Output: {output_file}") - - -def main(): - parser = argparse.ArgumentParser(description='Aggregate LLM grading results') - parser.add_argument('--inputs', nargs='+', required=True, - help='Input grade JSON files') - parser.add_argument('--out', required=True, - help='Output aggregated JSON file') - parser.add_argument('--summary', required=True, - help='Output summary Markdown file') - - args = parser.parse_args() - - aggregate_grades(args.inputs, args.out, args.summary) - - -if __name__ == '__main__': - main() diff --git a/.autograde/create_minimal_metadata.py b/.autograde/create_minimal_metadata.py deleted file mode 100644 index 75b3875..0000000 --- a/.autograde/create_minimal_metadata.py +++ /dev/null @@ -1,372 +0,0 @@ -#!/usr/bin/env python3 -""" -创建完整的成绩元数据文件 - -从 grade.json / final_grade.json / llm_grade.json 生成 metadata.json -包含所有详细信息：未通过的测试、各题详情等 -""" - -import json -import os -import sys -import re -from datetime import datetime - - -def extract_student_id(): - """从环境变量或仓库名中提取学生 ID""" - # 优先从环境变量获取 - student_id = os.getenv("STUDENT_ID") - if student_id: - return student_id - - # 从仓库名提取 - # 支持格式：org/assignment-stu_xxx 或 org/assignment-stu-xxx - repo = os.getenv("REPO", "") - if repo: - # 匹配 xxx-stu_yyy 或 xxx-stu-yyy 格式 - match = re.search(r'-stu[_-]([a-zA-Z0-9_]+)$', repo) - if match: - return match.group(1) - # 也尝试匹配 stu_xxx 在路径中的情况 - match = re.search(r'stu[_-]([a-zA-Z0-9_]+)', repo) - if match: - return match.group(1) - - return None - - -def extract_assignment_id(): - """从环境变量或仓库名中提取作业 ID""" - # 优先从环境变量获取 - assignment_id = os.getenv("ASSIGNMENT_ID") - if assignment_id: - return assignment_id - - # 从仓库名提取 - # 支持格式：org/assignment-stu_xxx 或 org/assignment-template - repo = os.getenv("REPO", "") - if repo: - # 取仓库名部分（去掉组织） - repo_name = repo.split("/")[-1] if "/" in repo else repo - - # 移除 -stu_xxx 或 -template 后缀 - assignment = re.sub(r'-stu[_-][a-zA-Z0-9_]+$', '', repo_name) - assignment = re.sub(r'-template$', '', assignment) - - if assignment: - return assignment - - return "unknown" - - -def create_final_metadata(final_grade_file='final_grade.json'): - """从 final_grade.json 创建元数据（期末大作业专用）""" - try: - with open(final_grade_file, 'r', encoding='utf-8') as f: - final_data = json.load(f) - - assignment_id = extract_assignment_id() - student_id = extract_student_id() - - total_score = final_data.get("total_score", 0) - max_score = final_data.get("max_score", 100) - breakdown = final_data.get("breakdown", {}) - - # 构建各组成部分 - components = [] - - # 编程测试部分 - prog = breakdown.get("programming", {}) - if prog: - prog_component = { - "type": "programming_java", - "score": prog.get("score", 0), - "max_score": prog.get("max_score", 80), - "details": { - "groups": prog.get("groups", {}) - } - } - components.append(prog_component) - - # REPORT.md 部分 - report = breakdown.get("report", {}) - if report: - report_component = { - "type": "llm_report", - "score": report.get("score", 0), - "max_score": report.get("max_score", 10), - "details": { - "flags": report.get("flags", []), - "confidence": report.get("confidence"), - "criteria": report.get("criteria", []) # LLM 各评分项及理由 - } - } - components.append(report_component) - - # FRONTEND.md 部分 - frontend = breakdown.get("frontend", {}) - if frontend: - frontend_component = { - "type": "llm_frontend", - "score": frontend.get("score", 0), - "max_score": frontend.get("max_score", 10), - "details": { - "flags": frontend.get("flags", []), - "confidence": frontend.get("confidence"), - "criteria": frontend.get("criteria", []) # LLM 各评分项及理由 - } - } - components.append(frontend_component) - - metadata = { - "version": "1.0", - "assignment": assignment_id, - "student_id": student_id, - "components": components, - "total_score": round(total_score, 2), - "total_max_score": max_score, - "timestamp": datetime.now().isoformat(), - "generator": "gitea-autograde" - } - - return metadata - except Exception as e: - print(f"Error creating final metadata: {e}", file=sys.stderr) - return {} - - -def create_grade_metadata(grade_file='grade.json'): - """从 grade.json 创建元数据，包含所有详细信息""" - try: - with open(grade_file, 'r') as f: - grade_data = json.load(f) - - assignment_id = extract_assignment_id() - student_id = extract_student_id() - language = os.getenv("LANGUAGE", "java") - - # 提取所有相关信息 - final_score = grade_data.get("final_score", grade_data.get("total_score", grade_data.get("score", 0))) - base_score = grade_data.get("base_score", final_score) - penalty = grade_data.get("penalty", 0) - passed = grade_data.get("passed", 0) - total = grade_data.get("total", 0) - fails = grade_data.get("fails", []) - max_score = grade_data.get("max_score", 100) - test_framework = grade_data.get("test_framework", "junit") - coverage = grade_data.get("coverage") - raw_score = grade_data.get("raw_score") - groups = grade_data.get("groups", {}) - - # 动态生成 type 字段 - type_map = { - "python": "programming_python", - "java": "programming_java", - "r": "programming_r" - } - component_type = type_map.get(language, f"programming_{language}") - - component = { - "type": component_type, - "language": language, - "score": round(final_score, 2), - "max_score": max_score, - "details": { - "passed": passed, - "total": total, - "base_score": round(base_score, 2), - "penalty": round(penalty, 2), - "coverage": round(coverage, 2) if coverage else None, - "raw_score": round(raw_score, 2) if raw_score else None, - "failed_tests": fails, - "test_framework": test_framework, - "groups": groups - } - } - - metadata = { - "version": "1.0", - "assignment": assignment_id, - "student_id": student_id, - "components": [component], - "total_score": round(final_score, 2), - "total_max_score": max_score, - "timestamp": datetime.now().isoformat(), - "generator": "gitea-autograde" - } - - return metadata - except Exception as e: - print(f"Error creating grade metadata: {e}", file=sys.stderr) - return {} - - -def create_llm_metadata(llm_grade_file='artifacts/llm_grade.json'): - """从 llm_grade.json 创建元数据，包含所有详细信息""" - try: - with open(llm_grade_file, 'r') as f: - llm_data = json.load(f) - - assignment_id = extract_assignment_id() - student_id = extract_student_id() - - # 提取聚合后的信息 - total_score = llm_data.get("total_score", llm_data.get("total", 0)) - max_score = llm_data.get("max_score", 30) - need_review = llm_data.get("need_review", False) - questions_data = llm_data.get("details", llm_data.get("questions", [])) - - # 构建各题详情 - question_details = [] - for i, q_data in enumerate(questions_data, 1): - q_score = q_data.get("total", q_data.get("score", 0)) - q_max = q_data.get("max_score", 10) - q_confidence = q_data.get("confidence", 1.0) - q_flags = q_data.get("flags", []) - q_need_review = "need_review" in q_flags or q_data.get("need_review", False) - q_criteria = q_data.get("criteria", []) - - # 规范化 criteria 格式 - formatted_criteria = [] - for crit in q_criteria: - formatted_criteria.append({ - "id": crit.get("id", ""), - "score": round(float(crit.get("score", 0)), 2), - "reason": crit.get("reason", "") - }) - - question_detail = { - "question_id": f"SA{i}", - "question_name": q_data.get("question", f"SA{i}"), - "score": round(float(q_score), 2), - "max_score": q_max, - "confidence": round(float(q_confidence), 2), - "need_review": q_need_review, - "flags": q_flags, - "criteria": formatted_criteria - } - question_details.append(question_detail) - - component = { - "type": "llm_essay", - "score": round(float(total_score), 2), - "max_score": max_score, - "details": { - "questions": len(question_details), - "need_review": need_review, - "question_details": question_details - } - } - - metadata = { - "version": "1.0", - "assignment": assignment_id, - "student_id": student_id, - "components": [component], - "total_score": round(float(total_score), 2), - "total_max_score": max_score, - "timestamp": datetime.now().isoformat(), - "generator": "gitea-autograde" - } - - return metadata - except Exception as e: - print(f"Error creating LLM metadata: {e}", file=sys.stderr) - return {} - - -def create_objective_metadata(objective_file='objective_grade.json'): - """从 objective_grade.json 创建元数据""" - try: - with open(objective_file, 'r', encoding='utf-8') as f: - objective_data = json.load(f) - - assignment_id = extract_assignment_id() - student_id = extract_student_id() - - total_score = objective_data.get("score", 0) - max_score = objective_data.get("max_score", 0) - components = objective_data.get("components", []) - - formatted_components = [] - for comp in components: - comp_type = comp.get("type", "objective") - formatted_components.append({ - "type": f"objective_{comp_type}", - "score": comp.get("score", 0), - "max_score": comp.get("max_score", 0), - "details": comp.get("details", {}) - }) - - if not formatted_components: - formatted_components.append({ - "type": "objective_total", - "score": total_score, - "max_score": max_score, - "details": {} - }) - - metadata = { - "version": "1.0", - "assignment": assignment_id, - "student_id": student_id, - "components": formatted_components, - "total_score": total_score, - "total_max_score": max_score, - "timestamp": datetime.now().isoformat(), - "generator": "gitea-autograde" - } - - return metadata - except Exception as e: - print(f"Error creating objective metadata: {e}", file=sys.stderr) - return {} - - -def main(): - """主函数""" - # 检查命令行参数或环境变量 - grade_type = os.getenv("GRADE_TYPE", "programming").lower() - grade_file_override = os.getenv("GRADE_FILE") - - if grade_type == "final": - # 期末大作业成绩（包含编程+报告） - final_file = grade_file_override or "final_grade.json" - if os.path.exists(final_file): - metadata = create_final_metadata(final_file) - else: - print(f"Error: {final_file} not found", file=sys.stderr) - metadata = {} - elif grade_type == "llm": - # LLM 成绩 - llm_file = grade_file_override or "artifacts/llm_grade.json" - if os.path.exists(llm_file): - metadata = create_llm_metadata(llm_file) - elif os.path.exists("llm_grade.json"): - metadata = create_llm_metadata("llm_grade.json") - else: - print(f"Error: {llm_file} not found", file=sys.stderr) - metadata = {} - elif grade_type == "objective": - objective_file = grade_file_override or "objective_grade.json" - if os.path.exists(objective_file): - metadata = create_objective_metadata(objective_file) - else: - print(f"Error: {objective_file} not found", file=sys.stderr) - metadata = {} - else: - # 编程成绩 - grade_file = grade_file_override or "grade.json" - if os.path.exists(grade_file): - metadata = create_grade_metadata(grade_file) - else: - print(f"Error: {grade_file} not found", file=sys.stderr) - metadata = {} - - # 输出到 stdout - print(json.dumps(metadata, ensure_ascii=False, indent=2)) - - -if __name__ == "__main__": - main() diff --git a/.autograde/generate_pdf_report.py b/.autograde/generate_pdf_report.py deleted file mode 100644 index 885836c..0000000 --- a/.autograde/generate_pdf_report.py +++ /dev/null @@ -1,815 +0,0 @@ -#!/usr/bin/env python3 -""" -生成专业的 PDF 成绩报告 - -适用于打印归档，包含： -- 封面页（课程信息、学生信息） -- 后端开发反思报告 -- 前端开发反思报告 -- 评分详情页 -- 防伪水印 -""" - -import argparse -import hashlib -import json -import os -import re -import sys -from datetime import datetime -from pathlib import Path - -try: - import markdown - from weasyprint import HTML, CSS - from weasyprint.text.fonts import FontConfiguration - HAS_PDF_SUPPORT = True -except ImportError: - HAS_PDF_SUPPORT = False - - -def load_json(filepath, default=None): - """安全加载 JSON 文件""" - if not os.path.exists(filepath): - return default or {} - try: - with open(filepath, "r", encoding="utf-8") as f: - return json.load(f) - except Exception as e: - print(f"Error loading {filepath}: {e}", file=sys.stderr) - return default or {} - - -def read_file(filepath): - """读取文件内容""" - if os.path.exists(filepath): - with open(filepath, "r", encoding="utf-8") as f: - return f.read() - return "" - - -def fix_image_paths(content, images_dir): - """修复图片路径为绝对路径""" - if not images_dir or not os.path.isdir(images_dir): - return content - - abs_images_dir = os.path.abspath(images_dir) - - def replace_img(match): - alt = match.group(1) - src = match.group(2) - if not src.startswith(('http://', 'https://', 'file://', '/')): - abs_src = os.path.join(abs_images_dir, os.path.basename(src)) - if os.path.exists(abs_src): - return f'![{alt}](file://{abs_src})' - return match.group(0) - - content = re.sub(r'!\[([^\]]*)\]\(([^)]+)\)', replace_img, content) - return content - - -def markdown_to_html(md_content): - """将 Markdown 转换为 HTML（仅内容部分）""" - extensions = ['tables', 'fenced_code', 'nl2br'] - return markdown.markdown(md_content, extensions=extensions) - - -def generate_watermark_id(student_id, commit_sha): - """生成唯一的水印标识""" - raw = f"{student_id}-{commit_sha}-{datetime.now().isoformat()}" - return hashlib.sha256(raw.encode()).hexdigest()[:16].upper() - - -def generate_cover_page(student_id, student_name="", class_name="", - assignment_name="VibeVault 期末大作业"): - """生成封面页 HTML""" - current_date = datetime.now().strftime('%Y年%m月%d日') - current_semester = "2025年秋季学期" - - # 如果有学生姓名，直接显示；否则留空供手写 - name_value = student_name if student_name else ' ' * 8 - class_value = class_name if class_name else ' ' * 8 - id_value = student_id if student_id else ' ' * 8 - - return f''' -
-
-
课程大作业报告
-
- -
-

《Java 程序设计》

-

期末大作业

-

{assignment_name}

-
- -
- - - - - - - - - - - - - - - - - -
学  号：{id_value}
姓  名：{name_value}
班  级：{class_value}
提交日期：{current_date}
-
- -
-

{current_semester}

-
-
- ''' - - -def generate_report_section(title, content, icon="📝"): - """生成报告章节 HTML""" - if not content or content.strip() in ['', '*（未提交）*']: - html_content = '

（未提交）

' - else: - html_content = markdown_to_html(content) - - return f''' -
-

{icon} {title}

-
- {html_content} -
-
- ''' - - -def generate_grade_page(final_grade): - """生成评分详情页 HTML""" - total = final_grade.get("total_score", 0) - max_score = final_grade.get("max_score", 100) - breakdown = final_grade.get("breakdown", {}) - - # 编程测试详情 - prog = breakdown.get("programming", {}) - prog_rows = "" - if prog.get("groups"): - for group_name, group_info in prog["groups"].items(): - prog_rows += f''' - - {group_name} - {group_info.get('passed', 0)} / {group_info.get('total', 0)} - {group_info.get('score', 0):.1f} - {group_info.get('max_score', 0)} - - ''' - - # LLM 评分详情 - def format_llm_details(section_data): - criteria = section_data.get("criteria", []) - if not criteria: - return f'

无详细评分

' - - rows = "" - for c in criteria: - reason = c.get("reason", "").replace("<", "<").replace(">", ">") - rows += f''' - - {c.get('id', '')} - {c.get('score', 0)} - {reason} - - ''' - - confidence = section_data.get("confidence") - flags = section_data.get("flags", []) - footer = "" - if confidence: - footer += f'置信度: {confidence:.2f}' - if flags: - footer += f'标记: {", ".join(flags)}' - - return f''' - - - - - {rows} -
评分项得分评语
-
{footer}
- ''' - - report = breakdown.get("report", {}) - frontend = breakdown.get("frontend", {}) - - return f''' -
-

📊 评分详情

- -
-
- {total:.1f} - / {max_score} -
-
总分
-
- -
-

成绩汇总

- - - - - - - - - - - - - - - - - - - - - - - - -
项目得分满分占比
编程测试{prog.get('score', 0):.1f}{prog.get('max_score', 80)}{prog.get('max_score', 80)}%
后端反思报告{report.get('score', 0):.1f}{report.get('max_score', 10)}{report.get('max_score', 10)}%
前端反思报告{frontend.get('score', 0):.1f}{frontend.get('max_score', 10)}{frontend.get('max_score', 10)}%
-
- -
-

编程测试详情

- - - - - {prog_rows or ''} -
测试组通过数得分满分
无测试数据
-
- -
-

后端反思报告评分

- {format_llm_details(report)} -
- -
-

前端反思报告评分

- {format_llm_details(frontend)} -
- -
-

报告生成时间：{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}

-

本报告由自动评分系统生成

-
-
- ''' - - -def get_css_styles(watermark_text="", commit_sha=""): - """获取 PDF 样式，包含水印和版本标记""" - - # 水印样式 - watermark_css = "" - if watermark_text: - watermark_css = f''' - /* 水印 */ - body::after {{ - content: "{watermark_text}"; - position: fixed; - top: 50%; - left: 50%; - transform: translate(-50%, -50%) rotate(-45deg); - font-size: 60pt; - color: rgba(200, 200, 200, 0.15); - white-space: nowrap; - pointer-events: none; - z-index: 9999; - }} - - .report-section::before, - .grade-page::before {{ - content: "{watermark_text}"; - position: absolute; - top: 50%; - left: 50%; - transform: translate(-50%, -50%) rotate(-45deg); - font-size: 48pt; - color: rgba(200, 200, 200, 0.12); - white-space: nowrap; - pointer-events: none; - z-index: -1; - }} - ''' - - # 版本标记（右上角） - commit_marker = "" - if commit_sha: - short_sha = commit_sha[:7] if len(commit_sha) > 7 else commit_sha - commit_marker = f''' - @top-right {{ - content: "{short_sha}"; - font-size: 8pt; - color: #999; - font-family: 'Consolas', 'Monaco', monospace; - }} - ''' - - return f''' - @page {{ - size: A4; - margin: 2cm 2.5cm; - {commit_marker} - @bottom-center {{ - content: counter(page); - font-size: 10pt; - color: #666; - }} - }} - - @page cover {{ - margin: 0; - @bottom-center {{ content: none; }} - }} - - @font-face {{ - font-family: 'Noto Sans CJK SC'; - src: local('Noto Sans CJK SC'), local('Noto Sans SC'), - local('Source Han Sans SC'), local('Source Han Sans CN'), - local('PingFang SC'), local('Microsoft YaHei'), - local('SimHei'), local('WenQuanYi Micro Hei'); - }} - - * {{ - margin: 0; - padding: 0; - box-sizing: border-box; - }} - - body {{ - font-family: 'Noto Sans CJK SC', 'Source Han Sans SC', 'PingFang SC', - 'Microsoft YaHei', 'SimHei', 'WenQuanYi Micro Hei', sans-serif; - font-size: 11pt; - line-height: 1.8; - color: #333; - }} - - {watermark_css} - - /* 封面页样式 */ - .cover-page {{ - page: cover; - height: 100vh; - display: flex; - flex-direction: column; - justify-content: center; - align-items: center; - text-align: center; - padding: 3cm; - page-break-after: always; - }} - - .cover-header {{ - margin-bottom: 4cm; - }} - - .university-name {{ - font-size: 18pt; - color: #1a5490; - letter-spacing: 0.5em; - font-weight: bold; - }} - - .cover-title h1 {{ - font-size: 26pt; - color: #1a5490; - margin-bottom: 0.5cm; - font-weight: bold; - }} - - .cover-title h2 {{ - font-size: 20pt; - color: #333; - margin-bottom: 0.3cm; - font-weight: normal; - }} - - .cover-title h3 {{ - font-size: 14pt; - color: #666; - font-weight: normal; - }} - - .cover-info {{ - margin-top: 3cm; - }} - - .info-table {{ - margin: 0 auto; - border-collapse: collapse; - }} - - .info-table td {{ - padding: 0.4cm 0.5cm; - font-size: 12pt; - }} - - .info-table .label {{ - text-align: right; - color: #333; - }} - - .info-table .value {{ - text-align: left; - min-width: 6cm; - }} - - .info-table .underline {{ - border-bottom: 1px solid #333; - }} - - .cover-footer {{ - margin-top: 4cm; - color: #666; - font-size: 11pt; - }} - - /* 报告章节样式 */ - .report-section {{ - page-break-before: always; - position: relative; - }} - - .section-title {{ - font-size: 18pt; - color: #1a5490; - border-bottom: 2px solid #1a5490; - padding-bottom: 0.3cm; - margin-bottom: 0.8cm; - }} - - .section-content {{ - text-align: justify; - }} - - .section-content h1 {{ - font-size: 16pt; - color: #1a5490; - margin: 1cm 0 0.5cm 0; - }} - - .section-content h2 {{ - font-size: 14pt; - color: #333; - margin: 0.8cm 0 0.4cm 0; - }} - - .section-content h3 {{ - font-size: 12pt; - color: #555; - margin: 0.6cm 0 0.3cm 0; - }} - - .section-content p {{ - margin: 0.4cm 0; - text-indent: 2em; - }} - - .section-content ul, .section-content ol {{ - margin: 0.4cm 0 0.4cm 1.5cm; - }} - - .section-content li {{ - margin: 0.2cm 0; - }} - - .section-content img {{ - max-width: 100%; - height: auto; - margin: 0.5cm auto; - display: block; - border: 1px solid #ddd; - }} - - .section-content code {{ - font-family: 'Consolas', 'Monaco', monospace; - background: #f5f5f5; - padding: 0.1cm 0.2cm; - border-radius: 3px; - font-size: 10pt; - }} - - .section-content pre {{ - background: #f5f5f5; - padding: 0.5cm; - border-radius: 5px; - overflow-x: auto; - font-size: 9pt; - margin: 0.5cm 0; - }} - - .section-content blockquote {{ - border-left: 4px solid #1a5490; - padding-left: 0.5cm; - margin: 0.5cm 0; - color: #555; - background: #f9f9f9; - padding: 0.3cm 0.5cm; - }} - - .section-content table {{ - width: 100%; - border-collapse: collapse; - margin: 0.5cm 0; - font-size: 10pt; - }} - - .section-content th, .section-content td {{ - border: 1px solid #ddd; - padding: 0.3cm; - text-align: left; - }} - - .section-content th {{ - background: #1a5490; - color: white; - }} - - .section-content tr:nth-child(even) {{ - background: #f9f9f9; - }} - - .empty-notice {{ - color: #999; - font-style: italic; - text-align: center; - padding: 2cm; - }} - - /* 评分页样式 */ - .grade-page {{ - page-break-before: always; - position: relative; - }} - - .page-title {{ - font-size: 18pt; - color: #1a5490; - text-align: center; - margin-bottom: 1cm; - }} - - .total-score {{ - text-align: center; - margin: 1cm 0; - }} - - .score-circle {{ - display: inline-block; - width: 4cm; - height: 4cm; - border: 4px solid #1a5490; - border-radius: 50%; - line-height: 4cm; - text-align: center; - }} - - .score-value {{ - font-size: 28pt; - font-weight: bold; - color: #1a5490; - }} - - .score-max {{ - font-size: 14pt; - color: #666; - }} - - .score-label {{ - font-size: 12pt; - color: #666; - margin-top: 0.3cm; - }} - - .grade-summary, .grade-details {{ - margin: 0.8cm 0; - }} - - .grade-summary h2, .grade-details h2 {{ - font-size: 14pt; - color: #333; - border-bottom: 1px solid #ddd; - padding-bottom: 0.2cm; - margin-bottom: 0.4cm; - }} - - .summary-table, .detail-table {{ - width: 100%; - border-collapse: collapse; - font-size: 10pt; - }} - - .summary-table th, .summary-table td, - .detail-table th, .detail-table td {{ - border: 1px solid #ddd; - padding: 0.25cm 0.4cm; - text-align: left; - }} - - .summary-table th, .detail-table th {{ - background: #1a5490; - color: white; - font-weight: normal; - }} - - .summary-table tr:nth-child(even), - .detail-table tr:nth-child(even) {{ - background: #f9f9f9; - }} - - .score-cell {{ - text-align: center; - font-weight: bold; - color: #1a5490; - }} - - .reason-cell {{ - font-size: 9pt; - color: #555; - max-width: 10cm; - }} - - .detail-footer {{ - font-size: 9pt; - color: #666; - margin-top: 0.2cm; - }} - - .detail-footer .confidence {{ - margin-right: 1cm; - }} - - .detail-footer .flags {{ - color: #c00; - }} - - .no-detail {{ - color: #999; - font-style: italic; - padding: 0.5cm; - text-align: center; - }} - - .grade-footer {{ - margin-top: 1cm; - padding-top: 0.5cm; - border-top: 1px solid #ddd; - font-size: 9pt; - color: #999; - text-align: center; - }} - - .grade-footer p {{ - margin: 0.1cm 0; - text-indent: 0; - }} - ''' - - -def create_full_html(args, final_grade, student_info): - """创建完整的 HTML 文档""" - - # 读取报告内容 - report_content = read_file(args.report) - frontend_content = read_file(args.frontend) - - # 修复图片路径 - frontend_content = fix_image_paths(frontend_content, args.images) - - # 移除报告中的标题行（避免重复） - report_content = re.sub(r'^#\s*后端开发反思报告.*\n', '', report_content, flags=re.MULTILINE) - frontend_content = re.sub(r'^#\s*前端开发反思报告.*\n', '', frontend_content, flags=re.MULTILINE) - - # 提取学生信息 - student_id = student_info.get("student_id", "") - student_name = student_info.get("name", "") - class_name = student_info.get("class_name", "") - commit_sha = student_info.get("commit_sha", "") - - # 生成水印文本 - watermark_text = "" - if student_id: - watermark_id = generate_watermark_id(student_id, commit_sha) - watermark_text = f"{student_id} · {watermark_id}" - - # 构建 HTML - html = f''' - - - - Java程序设计 - 期末大作业报告 - - - - {generate_cover_page(student_id, student_name, class_name)} - {generate_report_section("后端开发反思报告", report_content)} - {generate_report_section("前端开发反思报告", frontend_content, "🎨")} - {generate_grade_page(final_grade)} - -''' - - return html - - -def convert_to_pdf(html_content, pdf_file, images_dir=None): - """使用 weasyprint 生成 PDF""" - if not HAS_PDF_SUPPORT: - print("weasyprint not available", file=sys.stderr) - return False - - try: - font_config = FontConfiguration() - base_url = os.path.abspath(images_dir) if images_dir else os.getcwd() - - HTML(string=html_content, base_url=base_url).write_pdf( - pdf_file, - font_config=font_config - ) - return True - except Exception as e: - print(f"PDF generation error: {e}", file=sys.stderr) - return False - - -def main(): - parser = argparse.ArgumentParser(description="Generate professional PDF grade report") - parser.add_argument("--report", default="REPORT.md", help="REPORT.md file path") - parser.add_argument("--frontend", default="FRONTEND.md", help="FRONTEND.md file path") - parser.add_argument("--grade", default="final_grade.json", help="Final grade JSON file") - parser.add_argument("--images", default="images", help="Images directory") - parser.add_argument("--out", default="grade_report.pdf", help="Output PDF file") - parser.add_argument("--student-id", default="", help="Student ID") - parser.add_argument("--student-name", default="", help="Student name") - parser.add_argument("--class-name", default="", help="Class name") - parser.add_argument("--commit-sha", default="", help="Commit SHA for watermark") - args = parser.parse_args() - - # 从环境变量获取学生信息 - student_id = args.student_id or os.getenv("STUDENT_ID", "") - student_name = args.student_name or os.getenv("STUDENT_NAME", "") - class_name = args.class_name or os.getenv("CLASS_NAME", "") - commit_sha = args.commit_sha or os.getenv("COMMIT_SHA", "") - - # 从仓库名提取学生 ID - if not student_id: - repo = os.getenv("REPO", "") - match = re.search(r'-stu[_-]?st?(\d+)$', repo) - if match: - student_id = match.group(1) - else: - match = re.search(r'-stu[_-]([a-zA-Z0-9_]+)$', repo) - if match: - student_id = match.group(1) - - student_info = { - "student_id": student_id, - "name": student_name, - "class_name": class_name, - "commit_sha": commit_sha - } - - # 加载成绩 - final_grade = load_json(args.grade, {"total_score": 0, "max_score": 100, "breakdown": {}}) - - # 创建 HTML - html_content = create_full_html(args, final_grade, student_info) - - # 保存 HTML（调试用） - html_out = args.out.replace(".pdf", ".html") - with open(html_out, "w", encoding="utf-8") as f: - f.write(html_content) - - # 生成 PDF - if HAS_PDF_SUPPORT: - if convert_to_pdf(html_content, args.out, args.images): - print(f"✅ PDF report generated: {args.out}") - return 0 - else: - print(f"⚠️ PDF generation failed", file=sys.stderr) - return 1 - else: - print(f"ℹ️ weasyprint not installed, HTML saved: {html_out}") - return 0 - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/.autograde/grade.py b/.autograde/grade.py deleted file mode 100644 index c95734b..0000000 --- a/.autograde/grade.py +++ /dev/null @@ -1,187 +0,0 @@ -#!/usr/bin/env python3 -""" -编程题评分脚本 - -解析 JUnit XML 报告，计算分数，考虑迟交扣分，生成 grade.json 和 summary.md -""" - -import argparse -import xml.etree.ElementTree as ET -import json -import subprocess -import os -import time -import sys -from pathlib import Path -from dotenv import load_dotenv - -# 加载环境变量（支持从 .env 文件或环境变量读取） -load_dotenv() - - -def commit_ts(): - """获取最后一次提交的时间戳（Unix 时间戳）""" - try: - out = subprocess.check_output( - ["git", "log", "-1", "--format=%ct"], - stderr=subprocess.DEVNULL - ).decode().strip() - return int(out) - except Exception: - return int(time.time()) - - -def parse_junit(junit_path): - """ - 解析 JUnit XML 报告 - - Returns - ------- - passed : int - 通过的测试数 - total : int - 总测试数 - fails : list - 失败的测试名称列表 - """ - if not os.path.exists(junit_path): - return (0, 0, []) - - try: - root = ET.parse(junit_path).getroot() - total = 0 - passed = 0 - fails = [] - - for testsuite in root.iter("testsuite"): - for testcase in testsuite.iter("testcase"): - total += 1 - # 检查是否有 failure、error 或 skipped 子元素 - if list(testcase): - classname = testcase.get("classname", "") - name = testcase.get("name", "") - full_name = f"{classname}.{name}" if classname else name - fails.append(full_name) - else: - passed += 1 - - return (passed, total, fails) - except Exception as e: - print(f"Error parsing JUnit XML: {e}", file=sys.stderr) - return (0, 0, []) - - -def calculate_late_penalty(deadline_str): - """ - 计算迟交扣分 - - Parameters - ---------- - deadline_str : str - ISO 格式的截止时间（如 "2025-03-15T23:59:59+08:00"） - - Returns - ------- - penalty : float - 扣分数（0-30） - """ - if not deadline_str: - return 0.0 - - try: - # 解析截止时间（支持多种格式） - deadline_str = deadline_str.strip() - # 移除时区信息（简化处理） - if '+' in deadline_str: - deadline_str = deadline_str.split('+')[0] - elif 'Z' in deadline_str: - deadline_str = deadline_str.replace('Z', '') - - # 解析时间 - if 'T' in deadline_str: - dl = time.mktime(time.strptime(deadline_str[:19], "%Y-%m-%dT%H:%M:%S")) - else: - dl = time.mktime(time.strptime(deadline_str[:19], "%Y-%m-%d %H:%M:%S")) - - commit_time = commit_ts() - late_sec = max(0, commit_time - dl) - days = late_sec / 86400 - - # 扣分规则：第一天 10 分，之后每天 5 分，最多 30 分 - if days > 0: - penalty = min(30.0, 10.0 + 5.0 * days) - else: - penalty = 0.0 - - return round(penalty, 2) - except Exception as e: - print(f"Error calculating late penalty: {e}", file=sys.stderr) - return 0.0 - - -def main(): - parser = argparse.ArgumentParser(description="Grade programming assignments from JUnit XML") - parser.add_argument("--junit", required=True, help="Path to JUnit XML file") - parser.add_argument("--out", default="grade.json", help="Output JSON file") - parser.add_argument("--summary", default="summary.md", help="Output summary markdown file") - parser.add_argument("--bonus", default=None, help="Optional bonus file (e.g., lintr.rds)") - args = parser.parse_args() - - # 解析 JUnit XML - passed, total, fails = parse_junit(args.junit) - - # 计算基础分数 - if total > 0: - base_score = 100.0 * (passed / total) - else: - base_score = 0.0 - - # 计算迟交扣分 - deadline = os.getenv("DEADLINE", "") - penalty = calculate_late_penalty(deadline) - - # 最终分数 - final_score = max(0.0, round(base_score - penalty, 2)) - - # 生成 grade.json - grade_data = { - "score": final_score, - "base_score": round(base_score, 2), - "penalty": penalty, - "passed": passed, - "total": total, - "fails": fails, - "timestamp": int(time.time()) - } - - with open(args.out, "w", encoding="utf-8") as f: - json.dump(grade_data, f, ensure_ascii=False, indent=2) - - # 生成 summary.md - with open(args.summary, "w", encoding="utf-8") as f: - f.write("# 成绩报告\n\n") - f.write(f"- **通过用例**：{passed}/{total}\n") - f.write(f"- **原始分**：{base_score:.2f}/100\n") - if penalty > 0: - f.write(f"- **迟交扣分**：-{penalty:.2f}\n") - f.write(f"- **最终分**：**{final_score:.2f}/100**\n\n") - - if fails: - f.write("## 未通过的测试\n\n") - for fail in fails: - f.write(f"- {fail}\n") - f.write("\n") - - if deadline: - f.write(f"## 截止时间\n\n") - f.write(f"- 截止时间：{deadline}\n") - commit_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(commit_ts())) - f.write(f"- 提交时间：{commit_time_str}\n") - - print(f"Grading complete: {final_score:.2f}/100 ({passed}/{total} tests passed)") - - -if __name__ == "__main__": - main() - - diff --git a/.autograde/grade_grouped.py b/.autograde/grade_grouped.py deleted file mode 100644 index 9c7da3c..0000000 --- a/.autograde/grade_grouped.py +++ /dev/null @@ -1,207 +0,0 @@ -#!/usr/bin/env python3 -""" -分组编程题评分脚本 - -解析 JUnit XML 报告，按测试分组（Core/Advanced/Challenge）计算加权分数 -""" - -import argparse -import xml.etree.ElementTree as ET -import json -import os -import re -import sys -from pathlib import Path -from glob import glob - - -def parse_junit_files(junit_dir): - """ - 解析目录下所有 JUnit XML 报告 - - Returns - ------- - results : list of dict - 每个测试的结果，包含 classname, name, passed - """ - results = [] - - xml_files = glob(os.path.join(junit_dir, "TEST-*.xml")) - if not xml_files: - xml_files = glob(os.path.join(junit_dir, "*.xml")) - - for xml_file in xml_files: - try: - root = ET.parse(xml_file).getroot() - - for testsuite in root.iter("testsuite"): - for testcase in testsuite.iter("testcase"): - classname = testcase.get("classname", "") - name = testcase.get("name", "") - - # 检查是否有 failure、error 或 skipped 子元素 - failed = any(testcase.iter("failure")) or any(testcase.iter("error")) - skipped = any(testcase.iter("skipped")) - - results.append({ - "classname": classname, - "name": name, - "passed": not failed and not skipped, - "skipped": skipped - }) - except Exception as e: - print(f"Error parsing {xml_file}: {e}", file=sys.stderr) - - return results - - -def load_groups_config(groups_file): - """加载测试分组配置""" - if not os.path.exists(groups_file): - # 默认配置 - return { - "groups": { - "core": {"pattern": ".*core.*", "weight": 0.75, "max_score": 60}, - "advanced": {"pattern": ".*advanced.*", "weight": 0.125, "max_score": 10}, - "challenge": {"pattern": ".*challenge.*", "weight": 0.125, "max_score": 10} - }, - "fallback_group": "core" - } - - with open(groups_file, "r", encoding="utf-8") as f: - return json.load(f) - - -def categorize_test(classname, groups_config): - """根据 classname 将测试分类到对应的组""" - for group_name, group_info in groups_config.get("groups", {}).items(): - pattern = group_info.get("pattern", "") - if re.search(pattern, classname, re.IGNORECASE): - return group_name - - return groups_config.get("fallback_group", "core") - - -def calculate_grouped_score(test_results, groups_config): - """ - 按分组计算加权分数 - - Returns - ------- - dict - 包含各组得分和总分的字典 - """ - groups = groups_config.get("groups", {}) - - # 初始化各组统计 - group_stats = {} - for group_name, group_info in groups.items(): - group_stats[group_name] = { - "passed": 0, - "total": 0, - "max_score": group_info.get("max_score", 10), - "weight": group_info.get("weight", 0.1), - "tests": [] - } - - # 分类并统计测试结果 - for test in test_results: - group = categorize_test(test["classname"], groups_config) - if group not in group_stats: - group = groups_config.get("fallback_group", "core") - - group_stats[group]["total"] += 1 - if test["passed"]: - group_stats[group]["passed"] += 1 - else: - group_stats[group]["tests"].append(f"{test['classname']}.{test['name']}") - - # 计算各组得分 - total_score = 0 - group_scores = {} - - for group_name, stats in group_stats.items(): - if stats["total"] > 0: - pass_rate = stats["passed"] / stats["total"] - group_score = pass_rate * stats["max_score"] - else: - group_score = 0 - - group_scores[group_name] = { - "passed": stats["passed"], - "total": stats["total"], - "max_score": stats["max_score"], - "score": round(group_score, 2), - "failed_tests": stats["tests"][:10] # 只保留前 10 个失败测试 - } - - total_score += group_score - - return { - "total_score": round(total_score, 2), - "max_score": 80, # 编程测试总分 80 分（Core 60 + Advanced 10 + Challenge 10） - "groups": group_scores - } - - -def main(): - parser = argparse.ArgumentParser(description="Grade programming assignments with test groups") - parser.add_argument("--junit-dir", required=True, help="Directory containing JUnit XML files") - parser.add_argument("--groups", default="test_groups.json", help="Test groups configuration file") - parser.add_argument("--out", default="grade.json", help="Output JSON file") - parser.add_argument("--summary", default="summary.md", help="Output summary markdown file") - args = parser.parse_args() - - # 解析测试结果 - test_results = parse_junit_files(args.junit_dir) - - if not test_results: - print("Warning: No test results found", file=sys.stderr) - grade_data = { - "total_score": 0, - "max_score": 80, - "groups": {}, - "error": "No test results found" - } - else: - # 加载分组配置 - groups_config = load_groups_config(args.groups) - - # 计算分组分数 - grade_data = calculate_grouped_score(test_results, groups_config) - - # 保存 grade.json - with open(args.out, "w", encoding="utf-8") as f: - json.dump(grade_data, f, ensure_ascii=False, indent=2) - - # 生成 summary.md - with open(args.summary, "w", encoding="utf-8") as f: - f.write("# 编程测试成绩报告\n\n") - f.write(f"**总分：{grade_data['total_score']:.2f} / {grade_data['max_score']}**\n\n") - - f.write("## 分组得分\n\n") - f.write("| 分组 | 通过 | 总数 | 得分 | 满分 |\n") - f.write("|------|------|------|------|------|\n") - - for group_name, group_info in grade_data.get("groups", {}).items(): - f.write(f"| {group_name} | {group_info['passed']} | {group_info['total']} | " - f"{group_info['score']:.2f} | {group_info['max_score']} |\n") - - # 列出失败的测试 - all_failed = [] - for group_name, group_info in grade_data.get("groups", {}).items(): - all_failed.extend(group_info.get("failed_tests", [])) - - if all_failed: - f.write("\n## 未通过的测试\n\n") - for test in all_failed[:20]: # 最多显示 20 个 - f.write(f"- {test}\n") - if len(all_failed) > 20: - f.write(f"\n... 还有 {len(all_failed) - 20} 个未通过的测试\n") - - print(f"Grading complete: {grade_data['total_score']:.2f}/{grade_data['max_score']}") - - -if __name__ == "__main__": - main() - diff --git a/.autograde/llm_grade.py b/.autograde/llm_grade.py deleted file mode 100644 index 7d22602..0000000 --- a/.autograde/llm_grade.py +++ /dev/null @@ -1,249 +0,0 @@ -#!/usr/bin/env python3 -""" -LLM 简答题评分脚本 - -调用 LLM API，按评分量表对简答题进行评分，输出 JSON 格式结果 -""" - -import os -import json -import argparse -import requests -import sys -from pathlib import Path -from dotenv import load_dotenv - -# 加载环境变量（支持从 .env 文件或环境变量读取） -load_dotenv() - - -def read_file(path): - """读取文件内容""" - if os.path.exists(path): - return open(path, 'r', encoding='utf-8').read() - return "" - - -def read_file_or_string(value): - """ - 如果 value 是一个存在的文件路径，读取文件内容； - 否则直接返回 value 作为字符串。 - """ - if os.path.exists(value): - return open(value, 'r', encoding='utf-8').read() - return value # 当作字符串直接返回 - - -PROMPT_TEMPLATE = """你是严格且一致的助教，按提供的评分量表为学生的简答题评分。 - -评分规则： -- 严格依据量表中各评分项的 scoring_guide 进行评分 -- 每个评分项只能给出 scoring_guide 中定义的整数分值（如 0, 1, 2, 3, 4） -- 不输出任何解释性文本；只输出 JSON - -输出格式： -{{ - "total": number (各项分数之和), - "criteria": [ - {{"id": "评分项id", "score": 整数(必须是scoring_guide中定义的分值), "reason": "简短评语"}}, - ... - ], - "flags": [], - "confidence": number(0-1, 评分置信度) -}} - -重要： -- score 必须是整数，只能是 scoring_guide 中定义的分值（如 0/1/2/3/4） -- 不要给出 2.5, 3.5 这样的中间值 -- total 必须等于所有 criteria 的 score 之和 -- 如果答案与题目无关或为空，total=0，并加 flag "need_review" - -【题目】 -<<<{question}>>> - -【评分量表】 -<<<{rubric}>>> - -【学生答案】 -<<<{answer}>>> -""" - - -def call_llm(url, key, model, prompt): - """ - 调用 LLM API - - Parameters - ---------- - url : str - API 地址 - key : str - API 密钥 - model : str - 模型名称 - prompt : str - 提示词 - - Returns - ------- - dict - LLM 返回的 JSON 结果 - """ - headers = { - "Authorization": f"Bearer {key}", - "Content-Type": "application/json" - } - - data = { - "model": model, - "temperature": 0, - "top_p": 1, - "messages": [{"role": "user", "content": prompt}], - "response_format": {"type": "json_object"} - } - - try: - # 设置超时：连接超时 10 秒，读取超时 60 秒 - response = requests.post( - url, - headers=headers, - json=data, - timeout=(10, 60) - ) - response.raise_for_status() - result = response.json() - content = result.get("choices", [{}])[0].get("message", {}).get("content", "{}") - return json.loads(content) - except requests.exceptions.Timeout as e: - print(f"LLM API request timeout: {e}", file=sys.stderr) - raise - except requests.exceptions.HTTPError as e: - print(f"LLM API HTTP error: {e} (status: {response.status_code})", file=sys.stderr) - raise - except requests.exceptions.RequestException as e: - print(f"LLM API request failed: {e}", file=sys.stderr) - raise - except json.JSONDecodeError as e: - print(f"Failed to parse LLM response as JSON: {e}", file=sys.stderr) - raise - - -def main(): - parser = argparse.ArgumentParser(description="Grade short answer questions using LLM") - parser.add_argument("--question", required=True, help="Path to question file") - parser.add_argument("--answer", required=True, help="Path to answer file") - parser.add_argument("--rubric", required=True, help="Path to rubric JSON file") - parser.add_argument("--out", default="grade.json", help="Output JSON file") - parser.add_argument("--summary", default="summary.md", help="Output summary markdown file") - parser.add_argument("--model", default=os.getenv("LLM_MODEL", "deepseek-chat")) - parser.add_argument("--api_url", default=os.getenv("LLM_API_URL", "https://api.deepseek.com/chat/completions")) - parser.add_argument("--api_key", default=os.getenv("LLM_API_KEY", "")) - args = parser.parse_args() - - # 验证必需的配置 - if not args.api_key: - print("Warning: LLM_API_KEY not set. LLM grading may fail.", file=sys.stderr) - - # 读取文件或字符串 - # question 可以是文件路径或直接的问题字符串 - question = read_file_or_string(args.question).strip() - # answer 和 rubric 必须是文件路径 - answer = read_file(args.answer).strip() - rubric_text = read_file(args.rubric).strip() - - if not question or not answer: - print(f"Warning: Empty question or answer file", file=sys.stderr) - resp = { - "total": 0, - "criteria": [], - "flags": ["need_review", "empty_answer"], - "confidence": 0.0 - } - else: - # 调用 LLM - try: - prompt = PROMPT_TEMPLATE.format( - question=question, - rubric=rubric_text, - answer=answer - ) - resp = call_llm(args.api_url, args.api_key, args.model, prompt) - except Exception as e: - print(f"LLM grading failed: {e}", file=sys.stderr) - resp = { - "total": 0, - "criteria": [], - "flags": ["need_review", "llm_error"], - "confidence": 0.0 - } - - # 确保各项分数是整数，并重新计算 total - criteria = resp.get("criteria", []) - if criteria: - for c in criteria: - # 将分数四舍五入为整数（LLM 可能返回小数） - score = c.get("score", 0) - c["score"] = round(float(score)) - - # 重新计算 total（各项得分之和） - calculated_total = sum(c.get("score", 0) for c in criteria) - resp["total"] = calculated_total - - # 边界带自动送审 - try: - rubric_data = json.loads(rubric_text) - lo, hi = rubric_data.get("borderline_band", [None, None]) - total = float(resp.get("total", 0)) - flags = set(resp.get("flags", [])) - - if lo is not None and hi is not None and lo <= total <= hi: - flags.add("need_review") - - # 低置信度送审 - confidence = resp.get("confidence", 1.0) - if confidence < 0.7: - flags.add("need_review") - - resp["flags"] = sorted(list(flags)) - except Exception: - pass - - # 保存 grade.json - with open(args.out, "w", encoding="utf-8") as f: - json.dump(resp, f, ensure_ascii=False, indent=2) - - # 生成 summary.md - try: - rubric_data = json.loads(rubric_text) - max_score = rubric_data.get("max_score", 10) - except Exception: - max_score = 10 - - lines = [ - f"# 简答题评分", - f"", - f"- **总分**：**{resp.get('total', 0):.2f} / {max_score}**", - f"- **置信度**：{resp.get('confidence', 0):.2f}", - f"- **标记**：{', '.join(resp.get('flags', [])) or '无'}", - f"", - f"## 分项评分" - ] - - for criterion in resp.get("criteria", []): - criterion_id = criterion.get("id", "") - score = criterion.get("score", 0) - reason = criterion.get("reason", "") - lines.append(f"- **{criterion_id}**: {score} 分") - if reason: - lines.append(f" - {reason}") - - with open(args.summary, "w", encoding="utf-8") as f: - f.write("\n".join(lines)) - - print(f"LLM grading complete: {resp.get('total', 0):.2f}/{max_score}") - - -if __name__ == "__main__": - main() - - diff --git a/.autograde/objective_grade.py b/.autograde/objective_grade.py deleted file mode 100644 index dec7a41..0000000 --- a/.autograde/objective_grade.py +++ /dev/null @@ -1,444 +0,0 @@ -#!/usr/bin/env python3 -""" -选择题/判断题评分脚本 - -读取学生答案和标准答案，生成成绩 JSON 文件 -""" - -import json -import argparse -import sys -from datetime import datetime -from pathlib import Path - - -def load_answers(answer_file): - """ - 加载学生答案文件（支持 JSON 和简单文本格式） - - JSON 格式示例： - { - "MC1": "A", - "MC2": "B", - "TF1": true, - "TF2": false - } - - 文本格式示例（每行一个答案）： - A - B - true - false - """ - try: - with open(answer_file, 'r', encoding='utf-8') as f: - content = f.read().strip() - - # 尝试作为 JSON 加载 - if content.startswith('{'): - return json.loads(content) - - # 否则按行加载，忽略空行和注释 - lines = [line.strip() for line in content.split('\n') if line.strip() and not line.strip().startswith('#')] - - # 转换为字典格式：{"MC1": answer, "MC2": answer, ...} - answers = {} - for i, line in enumerate(lines, 1): - # 尝试识别题型 - if line.lower() in ('true', 'false', 't', 'f'): - question_id = f"TF{len([k for k in answers if k.startswith('TF')])+1}" - answers[question_id] = line.lower() in ('true', 't') - else: - question_id = f"MC{len([k for k in answers if k.startswith('MC')])+1}" - answers[question_id] = line.upper() - - return answers - except Exception as e: - print(f"Error loading answers: {e}", file=sys.stderr) - return {} - - -def load_standard_answers(std_file): - """加载标准答案文件（JSON 格式）""" - try: - with open(std_file, 'r', encoding='utf-8') as f: - return json.load(f) - except Exception as e: - print(f"Error loading standard answers: {e}", file=sys.stderr) - return {} - - -def grade_multiple_choice(student_answers, standard_answers, question_texts=None): - """ - 评选择题 - - Parameters - ---------- - student_answers : dict - 学生答案，格式 {"MC1": "A", "MC2": "B", ...} - standard_answers : dict - 标准答案，格式 {"MC1": "A", "MC2": "B", ...} - question_texts : dict, optional - 题目文本，格式 {"MC1": "题目文本", ...} - - Returns - ------- - dict - 成绩数据 - """ - questions = [] - correct_count = 0 - - for question_id, std_answer in standard_answers.items(): - if not question_id.startswith('MC'): - continue - - student_answer = student_answers.get(question_id, "") - is_correct = str(student_answer).upper() == str(std_answer).upper() - - if is_correct: - correct_count += 1 - score = 1 - else: - score = 0 - - questions.append({ - "question_id": question_id, - "question_text": question_texts.get(question_id, "") if question_texts else "", - "correct_answer": str(std_answer).upper(), - "student_answer": str(student_answer).upper(), - "correct": is_correct, - "score": score, - "max_score": 1 - }) - - total_count = len(questions) - - return { - "type": "multiple_choice", - "score": correct_count, - "max_score": total_count, - "details": { - "correct": correct_count, - "total": total_count, - "questions": questions - } - } - - -def grade_true_false(student_answers, standard_answers, question_texts=None): - """ - 评判断题 - - Parameters - ---------- - student_answers : dict - 学生答案，格式 {"TF1": true, "TF2": false, ...} - standard_answers : dict - 标准答案，格式 {"TF1": true, "TF2": false, ...} - question_texts : dict, optional - 题目文本 - - Returns - ------- - dict - 成绩数据 - """ - questions = [] - correct_count = 0 - - for question_id, std_answer in standard_answers.items(): - if not question_id.startswith('TF'): - continue - - student_answer = student_answers.get(question_id, None) - - # 规范化布尔值 - if isinstance(student_answer, str): - student_answer = student_answer.lower() in ('true', 't', '1', 'yes') - - is_correct = bool(student_answer) == bool(std_answer) - - if is_correct: - correct_count += 1 - score = 1 - else: - score = 0 - - questions.append({ - "question_id": question_id, - "question_text": question_texts.get(question_id, "") if question_texts else "", - "correct_answer": bool(std_answer), - "student_answer": bool(student_answer) if student_answer is not None else None, - "correct": is_correct, - "score": score, - "max_score": 1 - }) - - total_count = len(questions) - - return { - "type": "true_false", - "score": correct_count, - "max_score": total_count, - "details": { - "correct": correct_count, - "total": total_count, - "questions": questions - } - } - - -def grade_multiple_select(student_answers, standard_answers, question_texts=None): - """ - 评多选题 - - Parameters - ---------- - student_answers : dict - 学生答案，格式 {"MS1": ["A", "B"], "MS2": ["C"], ...} - standard_answers : dict - 标准答案，格式 {"MS1": ["A", "B"], "MS2": ["C"], ...} - question_texts : dict, optional - 题目文本 - - Returns - ------- - dict - 成绩数据 - """ - questions = [] - correct_count = 0 - - for question_id, std_answer in standard_answers.items(): - if not question_id.startswith('MS'): - continue - - student_answer = student_answers.get(question_id, []) - - # 规范化答案（转为大写并排序） - if isinstance(student_answer, str): - student_answer = [student_answer] - if not isinstance(student_answer, list): - student_answer = [] - - std_set = set([str(a).upper() for a in std_answer]) - stu_set = set([str(a).upper() for a in student_answer]) - - is_correct = std_set == stu_set - - if is_correct: - correct_count += 1 - score = 1 - else: - score = 0 - - questions.append({ - "question_id": question_id, - "question_text": question_texts.get(question_id, "") if question_texts else "", - "correct_answer": sorted(list(std_set)), - "student_answer": sorted(list(stu_set)) if stu_set else [], - "correct": is_correct, - "score": score, - "max_score": 1 - }) - - total_count = len(questions) - - return { - "type": "multiple_select", - "score": correct_count, - "max_score": total_count, - "details": { - "correct": correct_count, - "total": total_count, - "questions": questions - } - } - - -def grade_fill_blank(student_answers, standard_answers, question_texts=None): - """ - 评填空题 - - Parameters - ---------- - student_answers : dict - 学生答案，格式 {"FB1": "答案", "FB2": ["答案1", "答案2"], ...} - standard_answers : dict - 标准答案，格式同上 - question_texts : dict, optional - 题目文本 - - Returns - ------- - dict - 成绩数据 - """ - questions = [] - correct_count = 0 - - def normalize_answer(ans): - """规范化答案：去除空格、转小写""" - if isinstance(ans, str): - return ans.strip().lower() - elif isinstance(ans, list): - return [a.strip().lower() for a in ans] - return ans - - def compare_answers(student, standard): - """比较答案是否相等""" - student_norm = normalize_answer(student) - standard_norm = normalize_answer(standard) - - if isinstance(standard_norm, list) and isinstance(student_norm, list): - return student_norm == standard_norm - elif isinstance(standard_norm, str) and isinstance(student_norm, str): - return student_norm == standard_norm - return False - - for question_id, std_answer in standard_answers.items(): - if not question_id.startswith('FB'): - continue - - student_answer = student_answers.get(question_id, "") - - is_correct = compare_answers(student_answer, std_answer) - - if is_correct: - correct_count += 1 - score = 1 - else: - score = 0 - - questions.append({ - "question_id": question_id, - "question_text": question_texts.get(question_id, "") if question_texts else "", - "correct_answer": std_answer, - "student_answer": student_answer, - "correct": is_correct, - "score": score, - "max_score": 1 - }) - - total_count = len(questions) - - return { - "type": "fill_blank", - "score": correct_count, - "max_score": total_count, - "details": { - "correct": correct_count, - "total": total_count, - "questions": questions - } - } - - -def main(): - parser = argparse.ArgumentParser(description="Grade objective questions") - parser.add_argument("--answers", required=True, help="Student answers file (JSON or text)") - parser.add_argument("--standard", required=True, help="Standard answers file (JSON)") - parser.add_argument("--questions", help="Question texts file (JSON, optional)") - parser.add_argument("--out", default="grade.json", help="Output grade JSON file") - parser.add_argument("--summary", default="summary.md", help="Output summary markdown file") - parser.add_argument("--type", choices=['mc', 'tf', 'ms', 'fb', 'all'], default='all', - help="Question type to grade") - - args = parser.parse_args() - - # 加载文件 - student_answers = load_answers(args.answers) - standard_answers = load_standard_answers(args.standard) - question_texts = None - - if args.questions: - try: - with open(args.questions, 'r', encoding='utf-8') as f: - question_texts = json.load(f) - except Exception as e: - print(f"Warning: Could not load question texts: {e}", file=sys.stderr) - - if not student_answers or not standard_answers: - print("Error: Could not load answers", file=sys.stderr) - sys.exit(1) - - # 评分 - components = [] - total_score = 0 - total_max_score = 0 - - if args.type in ('mc', 'all'): - mc_grade = grade_multiple_choice(student_answers, standard_answers, question_texts) - if mc_grade['details']['total'] > 0: - components.append(mc_grade) - total_score += mc_grade['score'] - total_max_score += mc_grade['max_score'] - - if args.type in ('tf', 'all'): - tf_grade = grade_true_false(student_answers, standard_answers, question_texts) - if tf_grade['details']['total'] > 0: - components.append(tf_grade) - total_score += tf_grade['score'] - total_max_score += tf_grade['max_score'] - - if args.type in ('ms', 'all'): - ms_grade = grade_multiple_select(student_answers, standard_answers, question_texts) - if ms_grade['details']['total'] > 0: - components.append(ms_grade) - total_score += ms_grade['score'] - total_max_score += ms_grade['max_score'] - - if args.type in ('fb', 'all'): - fb_grade = grade_fill_blank(student_answers, standard_answers, question_texts) - if fb_grade['details']['total'] > 0: - components.append(fb_grade) - total_score += fb_grade['score'] - total_max_score += fb_grade['max_score'] - - # 生成 grade.json - grade_data = { - "score": total_score, - "max_score": total_max_score, - "components": components, - "timestamp": int(__import__('time').time()) - } - - with open(args.out, 'w', encoding='utf-8') as f: - json.dump(grade_data, f, ensure_ascii=False, indent=2) - - # 生成 summary.md - summary_lines = [ - "# 客观题评分\n", - f"- **总分**：{total_score} / {total_max_score}\n", - f"- **组件数**：{len(components)}\n", - "" - ] - - for comp in components: - comp_type = comp['type'] - correct = comp['details']['correct'] - total = comp['details']['total'] - - type_names = { - 'multiple_choice': '选择题', - 'true_false': '判断题', - 'multiple_select': '多选题', - 'fill_blank': '填空题' - } - - type_name = type_names.get(comp_type, comp_type) - summary_lines.append(f"## {type_name}\n") - summary_lines.append(f"- **正确**：{correct} / {total}\n") - summary_lines.append("") - - with open(args.summary, 'w', encoding='utf-8') as f: - f.write("\n".join(summary_lines)) - - print(f"Grading complete: {total_score}/{total_max_score}") - return 0 - - -if __name__ == "__main__": - sys.exit(main()) - diff --git a/.autograde/post_comment.py b/.autograde/post_comment.py deleted file mode 100644 index 4040b74..0000000 --- a/.autograde/post_comment.py +++ /dev/null @@ -1,155 +0,0 @@ -#!/usr/bin/env python3 -""" -发送评论到 Gitea PR - -从环境变量读取配置，发送评论到指定的 PR -支持在 Markdown 评论中嵌入 JSON 数据，便于后续结构化提取 -""" - -import os -import sys -import json -import requests -from datetime import datetime - - -def create_comment_with_metadata(summary, commit_sha, comment_type='grade', metadata=None): - """ - 创建包含元数据的评论内容 - - Parameters - ---------- - summary : str - 人类可读的 Markdown 格式总结 - commit_sha : str - 提交 SHA - comment_type : str - 评论类型 ('grade', 'llm', 'combined') - metadata : dict, optional - 结构化的成绩数据，将嵌入为 JSON - - Returns - ------- - str - 完整的评论内容（Markdown + JSON） - """ - commit_short = commit_sha[:7] if commit_sha else 'unknown' - - # 根据类型设置标题和图标 - if comment_type == 'llm': - title = "🤖 LLM 简答题评分结果" - footer = "*此评论由 Gitea Actions 自动生成（使用 DeepSeek API） | Commit: `{}`*" - elif comment_type == 'combined': - title = "📊 综合评分结果" - footer = "*此评论由 Gitea Actions 自动生成 | Commit: `{}`*" - else: - title = "🤖 自动评分结果" - footer = "*此评论由 Gitea Actions 自动生成 | Commit: `{}`*" - - # 构建评论 - parts = [ - f"## {title}", - "", - summary, - "" - ] - - # 如果提供了元数据，嵌入 JSON - if metadata: - # 确保元数据包含版本和时间戳 - if 'version' not in metadata: - metadata['version'] = '1.0' - if 'timestamp' not in metadata: - metadata['timestamp'] = datetime.now().isoformat() - - # 使用 Markdown 代码块嵌入 JSON（更可靠，Gitea 会保留） - # 放在评论末尾，对学生不太显眼 - json_str = json.dumps(metadata, ensure_ascii=False, indent=2) - parts.extend([ - "", - "---", - "", - "", - "```json", - json_str, - "```", - "" - ]) - - parts.extend([ - footer.format(commit_short) - ]) - - return "\n".join(parts) - - -def main(): - # 从环境变量读取配置 - api_url = os.environ.get('API_URL', '') - repo = os.environ.get('REPO', '') - pr_number = os.environ.get('PR_NUMBER', '') - token = os.environ.get('GITEA_TOKEN', '') - summary = os.environ.get('SUMMARY', '') - commit_sha = os.environ.get('COMMIT_SHA', '') - comment_type = os.environ.get('COMMENT_TYPE', 'grade') - - # 可选：从环境变量读取 JSON 元数据 - metadata_str = os.environ.get('GRADE_METADATA', '') - metadata = None - if metadata_str: - try: - metadata = json.loads(metadata_str) - except json.JSONDecodeError as e: - print(f"Warning: Failed to parse GRADE_METADATA: {e}", file=sys.stderr) - - # 验证必需参数 - if not all([api_url, repo, pr_number, token, summary]): - print("Error: Missing required environment variables", file=sys.stderr) - print(f"API_URL: {api_url}", file=sys.stderr) - print(f"REPO: {repo}", file=sys.stderr) - print(f"PR_NUMBER: {pr_number}", file=sys.stderr) - print(f"GITEA_TOKEN: {'set' if token else 'not set'}", file=sys.stderr) - print(f"SUMMARY: {'set' if summary else 'not set'}", file=sys.stderr) - sys.exit(1) - - # 构建评论内容（包含元数据） - comment_body = create_comment_with_metadata( - summary=summary, - commit_sha=commit_sha, - comment_type=comment_type, - metadata=metadata - ) - - # 构建 API URL - comment_url = f"{api_url}/repos/{repo}/issues/{pr_number}/comments" - - # 发送请求 - headers = { - "Authorization": f"token {token}", - "Content-Type": "application/json" - } - - data = {"body": comment_body} - - try: - print(f"Posting comment to: {comment_url}") - if metadata: - print("✓ Comment includes structured metadata") - response = requests.post(comment_url, headers=headers, json=data, timeout=30) - response.raise_for_status() - print("✅ Comment posted successfully to PR") - return 0 - except requests.exceptions.Timeout: - print("⚠️ Request timeout", file=sys.stderr) - return 1 - except requests.exceptions.HTTPError as e: - print(f"⚠️ HTTP error: {e}", file=sys.stderr) - print(f"Response: {response.text}", file=sys.stderr) - return 1 - except Exception as e: - print(f"⚠️ Failed to post comment: {e}", file=sys.stderr) - return 1 - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/.autograde/run_tests.py b/.autograde/run_tests.py deleted file mode 100644 index 9726f92..0000000 --- a/.autograde/run_tests.py +++ /dev/null @@ -1,164 +0,0 @@ -#!/usr/bin/env python3 -""" -通用测试运行器 - 根据语言配置运行测试并生成 JUnit XML - -支持的语言: -- python: pytest -- java: maven (mvn test) -- r: testthat (通过 JUnit Reporter) - -环境变量: -- LANGUAGE: 编程语言 (python/java/r) -- TEST_DIR: 测试目录路径 -- SOURCE_DIR: 源代码目录路径 -""" - -import argparse -import subprocess -import sys -import os -from pathlib import Path - - -def run_python_tests(test_dir, output_xml, **kwargs): - """运行 Python pytest 测试""" - cmd = [ - "pytest", test_dir, - f"--junit-xml={output_xml}", - "-v", "--tb=short" - ] - - # 添加覆盖率选项（如果指定） - source_dir = kwargs.get('source_dir') - if source_dir: - cmd.extend([ - f"--cov={source_dir}", - "--cov-report=term-missing", - "--cov-report=json:coverage.json" - ]) - - print(f"Running: {' '.join(cmd)}") - result = subprocess.run(cmd, capture_output=False) - return result - - -def run_java_tests(test_dir, output_xml, **kwargs): - """运行 Java Maven 测试""" - cmd = ["mvn", "test", "-B"] - - print(f"Running: {' '.join(cmd)}") - result = subprocess.run(cmd, capture_output=False) - - # Maven 自动生成 XML 在 target/surefire-reports/ - # 需要复制到指定的输出位置 - surefire_dir = Path("target/surefire-reports") - if surefire_dir.exists(): - # 合并所有 TEST-*.xml 文件 - import xml.etree.ElementTree as ET - - xml_files = list(surefire_dir.glob("TEST-*.xml")) - if xml_files: - # 简单情况：只复制第一个（或合并） - import shutil - if len(xml_files) == 1: - shutil.copy(xml_files[0], output_xml) - else: - # 合并多个 XML 文件（简化版本） - root = ET.Element("testsuites") - for xml_file in xml_files: - tree = ET.parse(xml_file) - root.append(tree.getroot()) - - tree = ET.ElementTree(root) - tree.write(output_xml, encoding='utf-8', xml_declaration=True) - - return result - - -def run_r_tests(test_dir, output_xml, **kwargs): - """运行 R testthat 测试""" - # R 脚本：使用 testthat 的 JUnitReporter - # 注意：需要安装 testthat (>= 3.0.0) - - r_script = f""" -library(testthat) - -# 配置 JUnit reporter -reporter <- JunitReporter$new(file = '{output_xml}') - -# 运行测试 -test_dir( - path = '{test_dir}', - reporter = reporter, - stop_on_failure = FALSE -) -""" - - # 将脚本写入临时文件 - import tempfile - with tempfile.NamedTemporaryFile(mode='w', suffix='.R', delete=False) as f: - f.write(r_script) - script_path = f.name - - try: - cmd = ["Rscript", script_path] - print(f"Running: {' '.join(cmd)}") - result = subprocess.run(cmd, capture_output=False) - return result - finally: - # 清理临时文件 - if os.path.exists(script_path): - os.remove(script_path) - - -def main(): - parser = argparse.ArgumentParser( - description="通用测试运行器 - 支持 Python/Java/R" - ) - parser.add_argument( - "--language", - required=True, - choices=["python", "java", "r"], - help="编程语言" - ) - parser.add_argument( - "--test-dir", - required=True, - help="测试目录路径" - ) - parser.add_argument( - "--output-xml", - default="test-results.xml", - help="JUnit XML 输出文件路径" - ) - parser.add_argument( - "--source-dir", - help="源代码目录（用于覆盖率）" - ) - - args = parser.parse_args() - - # 语言对应的运行器 - runners = { - "python": run_python_tests, - "java": run_java_tests, - "r": run_r_tests, - } - - if args.language not in runners: - print(f"❌ Unsupported language: {args.language}", file=sys.stderr) - sys.exit(1) - - # 运行测试 - result = runners[args.language]( - args.test_dir, - args.output_xml, - source_dir=args.source_dir - ) - - sys.exit(result.returncode) - - -if __name__ == "__main__": - main() - diff --git a/.autograde/test_objective_grade.sh b/.autograde/test_objective_grade.sh deleted file mode 100644 index f233eaa..0000000 --- a/.autograde/test_objective_grade.sh +++ /dev/null @@ -1,95 +0,0 @@ -#!/bin/bash -# 测试客观题评分脚本 - -set -e - -echo "=== 测试客观题评分脚本 ===" - -cd "$(dirname "$0")/.." - -# 测试 1: 使用 JSON 格式答案 -echo "" -echo "测试 1: JSON 格式答案（全对）" -python3 ./.autograde/objective_grade.py \ - --answers objective_questions/standard_answers.json \ - --standard objective_questions/standard_answers.json \ - --questions objective_questions/question_texts.json \ - --out test_grade1.json \ - --summary test_summary1.md \ - --type both - -echo "分数：" -python3 -c "import json; data=json.load(open('test_grade1.json')); print(f\"{data['score']}/{data['max_score']}\")" - -echo "" -echo "摘要：" -cat test_summary1.md - -# 测试 2: 使用部分错误的答案 -echo "" -echo "测试 2: 部分错误答案" -cat > test_answers2.json << 'EOF' -{ - "MC1": "A", - "MC2": "A", - "MC3": "C", - "MC4": "B", - "MC5": "C", - "TF1": true, - "TF2": false, - "TF3": true, - "TF4": true, - "TF5": false -} -EOF - -python3 ./.autograde/objective_grade.py \ - --answers test_answers2.json \ - --standard objective_questions/standard_answers.json \ - --questions objective_questions/question_texts.json \ - --out test_grade2.json \ - --summary test_summary2.md \ - --type both - -echo "分数：" -python3 -c "import json; data=json.load(open('test_grade2.json')); print(f\"{data['score']}/{data['max_score']}\")" - -echo "" -echo "摘要：" -cat test_summary2.md - -# 测试 3: 只评选择题 -echo "" -echo "测试 3: 只评选择题" -python3 ./.autograde/objective_grade.py \ - --answers objective_questions/standard_answers.json \ - --standard objective_questions/standard_answers.json \ - --questions objective_questions/question_texts.json \ - --out test_grade3.json \ - --summary test_summary3.md \ - --type mc - -echo "分数：" -python3 -c "import json; data=json.load(open('test_grade3.json')); print(f\"{data['score']}/{data['max_score']}\")" - -# 测试 4: 只评判断题 -echo "" -echo "测试 4: 只评判断题" -python3 ./.autograde/objective_grade.py \ - --answers objective_questions/standard_answers.json \ - --standard objective_questions/standard_answers.json \ - --questions objective_questions/question_texts.json \ - --out test_grade4.json \ - --summary test_summary4.md \ - --type tf - -echo "分数：" -python3 -c "import json; data=json.load(open('test_grade4.json')); print(f\"{data['score']}/{data['max_score']}\")" - -# 清理测试文件 -rm -f test_grade*.json test_summary*.md test_answers*.json - -echo "" -echo "✅ 所有测试通过！" - - diff --git a/.autograde/upload_metadata.py b/.autograde/upload_metadata.py deleted file mode 100644 index 8341ac5..0000000 --- a/.autograde/upload_metadata.py +++ /dev/null @@ -1,157 +0,0 @@ -#!/usr/bin/env python3 -""" -Upload metadata.json to teacher-only repository via Gitea API. -""" - -import argparse -import base64 -import json -import os -import sys -import urllib.error -import urllib.request -from pathlib import Path -from urllib.parse import urlparse - - -def detect_host(server_url: str, external_host: str | None) -> str: - """Detect the Gitea host to use for API calls. - - If server_url uses internal name (like 'gitea'), use external_host instead. - """ - parsed = urlparse(server_url) - raw_host = parsed.netloc or parsed.path.split("/")[0] - host = raw_host - if raw_host.lower().startswith("gitea"): - if not external_host: - raise ValueError( - f"Server URL uses internal name '{raw_host}' but EXTERNAL_GITEA_HOST is not set. " - "Please configure EXTERNAL_GITEA_HOST in .env and run sync_runner_config.sh" - ) - host = external_host - return host - - -def main() -> int: - parser = argparse.ArgumentParser(description="Upload metadata.json to course metadata repo") - parser.add_argument("--metadata-file", required=True) - parser.add_argument("--metadata-repo", required=True, help="owner/repo of metadata store") - parser.add_argument("--branch", default="main") - parser.add_argument("--student-repo", required=True) - parser.add_argument("--run-id", required=True) - parser.add_argument("--commit-sha", required=True) - parser.add_argument("--workflow", required=True, choices=["grade", "objective", "llm"]) - parser.add_argument("--server-url", required=True) - parser.add_argument("--external-host") - parser.add_argument("--assignment-id", help="Assignment ID (e.g., hw1)") - args = parser.parse_args() - - token = os.environ.get("METADATA_TOKEN") - if not token: - print("METADATA_TOKEN is not set", file=sys.stderr) - return 1 - - path = Path(args.metadata_file) - if not path.is_file(): - print(f"metadata file not found: {path}", file=sys.stderr) - return 0 - - try: - owner, repo_name = args.metadata_repo.split("/", 1) - except ValueError: - print(f"Invalid metadata repo: {args.metadata_repo}", file=sys.stderr) - return 1 - - # Extract student ID from student repo name - # student repo format: hw1-stu_20250001 or hw1-stu_student1 - student_id = args.student_repo.split("/")[-1] # Get repo name - - # Auto-detect assignment ID from student repo if not provided - assignment_id = args.assignment_id - if not assignment_id: - # Try to extract from student_repo format: hw1-stu_xxx - repo_name_part = args.student_repo.split("/")[-1] - if "-stu_" in repo_name_part: - assignment_id = repo_name_part.split("-stu_")[0] - elif "-template" in repo_name_part: - assignment_id = repo_name_part.split("-template")[0] - elif "-tests" in repo_name_part: - assignment_id = repo_name_part.split("-tests")[0] - else: - assignment_id = "unknown" - - # New path structure: {assignment_id}/{student_id}/{workflow}_{run_id}_{sha}.json - target_path = f"{assignment_id}/{student_id}/{args.workflow}_{args.run_id}_{args.commit_sha[:7]}.json" - - host = detect_host(args.server_url, args.external_host) - api_url = f"http://{host}/api/v1/repos/{owner}/{repo_name}/contents/{target_path}" - message = f"Upload {args.workflow} metadata for {args.student_repo} {args.commit_sha}" - - # Check if file exists to determine if we need to update (PUT) or create (POST) - get_req = urllib.request.Request( - api_url, - headers={"Authorization": f"token {token}"}, - method="GET" - ) - - sha = None - try: - with urllib.request.urlopen(get_req) as resp: - existing_file = json.loads(resp.read().decode()) - # API may return a list (directory contents) or dict (single file) - if isinstance(existing_file, dict): - sha = existing_file.get("sha") - print(f"File exists, updating (sha: {sha})") - elif isinstance(existing_file, list): - # Response is a directory listing, file doesn't exist at this exact path - print(f"Path is a directory or file not found in expected format") - else: - print(f"Unexpected response type: {type(existing_file)}") - except urllib.error.HTTPError as e: - if e.code != 404: - print(f"Error checking file existence: {e}", file=sys.stderr) - return 1 - # File doesn't exist, proceed with creation - - content = base64.b64encode(path.read_bytes()).decode() - payload = { - "content": content, - "message": message, - "branch": args.branch - } - - if sha: - payload["sha"] = sha - - data = json.dumps(payload).encode() - - req = urllib.request.Request( - api_url, - data=data, - headers={ - "Authorization": f"token {token}", - "Content-Type": "application/json", - }, - method="PUT" if sha else "POST", - ) - - try: - with urllib.request.urlopen(req, timeout=30) as resp: - resp_body = resp.read().decode() - print(resp_body) - except urllib.error.HTTPError as exc: - print(f"Metadata upload failed: {exc.status} {exc.reason}", file=sys.stderr) - print(exc.read().decode(), file=sys.stderr) - return 1 - except urllib.error.URLError as exc: - print(f"Metadata upload failed: {exc}", file=sys.stderr) - return 1 - - print(f"✅ Metadata stored at {args.metadata_repo}:{target_path}") - return 0 - - -if __name__ == "__main__": - raise SystemExit(main()) - - diff --git a/.autograde/workflow_templates/README.md b/.autograde/workflow_templates/README.md deleted file mode 100644 index 4f42a13..0000000 --- a/.autograde/workflow_templates/README.md +++ /dev/null @@ -1,216 +0,0 @@ -# Workflow 模板 - -本目录包含不同编程语言的 Gitea Actions workflow 模板。 - -## 可用模板 - -| 文件 | 语言 | 容器 | 测试框架 | -|------|------|------|----------| -| `python.yml` | Python | python:3.11 | pytest | -| `java.yml` | Java | maven:3.9-eclipse-temurin-17 | JUnit 5 | -| `r.yml` | R | r-base:4.3 | testthat | - -## 使用方法 - -### 1. 选择模板 - -根据你的编程语言选择对应的模板： - -```bash -# 对于 Python 作业 -cp .autograde/workflow_templates/python.yml .gitea/workflows/grade.yml - -# 对于 Java 作业 -cp .autograde/workflow_templates/java.yml .gitea/workflows/grade.yml - -# 对于 R 作业 -cp .autograde/workflow_templates/r.yml .gitea/workflows/grade.yml -``` - -### 2. 自定义配置 - -编辑 `.gitea/workflows/grade.yml` 根据需要修改： - -- **容器版本**：修改 `container:` 字段 -- **超时时间**：修改 `timeout-minutes:` -- **依赖安装**：修改 "Install dependencies" 步骤 -- **测试命令**：修改测试运行步骤 - -### 3. 配置 Secrets - -确保在 Gitea 仓库设置中配置了以下 Secrets： - -- `TESTS_TOKEN`：用于访问隐藏测试仓库的 token（可选） -- `EXTERNAL_GITEA_HOST`：外部访问的 Gitea 地址（可选） - -## Python 模板 (python.yml) - -### 特点 -- 使用 `python:3.11` 容器 -- 自动安装 `requirements.txt` 中的依赖 -- 使用 `run_tests.py` 运行 pytest -- 支持代码覆盖率 - -### 自定义选项 -```yaml -# 修改 Python 版本 -container: python:3.10 # 或 python:3.9 - -# 添加额外的依赖 -- name: Install dependencies - run: | - pip install -r requirements.txt - pip install numpy pandas # 额外的包 -``` - -## Java 模板 (java.yml) - -### 特点 -- 使用 `maven:3.9-eclipse-temurin-17` 容器 -- Maven 自动管理依赖（通过 `pom.xml`） -- JUnit 5 测试框架 -- 自动提取 Surefire 报告 - -### 自定义选项 -```yaml -# 修改 JDK 版本 -container: maven:3.9-eclipse-temurin-11 # Java 11 -container: maven:3.9-eclipse-temurin-21 # Java 21 - -# 自定义 Maven 命令 -run: | - mvn clean test -B -DskipTests=false -``` - -### Maven 配置提示 - -确保 `pom.xml` 中配置了 Surefire 插件： - -```xml - - org.apache.maven.plugins - maven-surefire-plugin - 3.2.2 - - ${project.build.directory}/surefire-reports - - -``` - -## R 模板 (r.yml) - -### 特点 -- 使用 `r-base:4.3` 容器 -- 自动从 `DESCRIPTION` 安装依赖 -- testthat 测试框架 -- JUnitReporter 输出 XML - -### 自定义选项 -```yaml -# 修改 R 版本 -container: r-base:4.2 # 或其他版本 - -# 修改 CRAN 镜像 -run: | - Rscript -e "install.packages('testthat', repos='https://cran.r-project.org/')" -``` - -### R 项目结构要求 - -``` -project/ -├── DESCRIPTION # 包依赖定义 -├── R/ # R 源代码 -└── tests/ - └── testthat/ # testthat 测试 -``` - -## 通用 Workflow 流程 - -所有模板都遵循相同的流程： - -1. **安装系统依赖**（git, rsync 等） -2. **检出代码** - 克隆学生仓库 -3. **安装语言依赖** - 根据语言安装包 -4. **获取隐藏测试**（可选）- 从私有仓库获取 -5. **运行测试** - 生成 JUnit XML -6. **评分** - 解析 XML，计算分数 -7. **生成元数据** - 创建 JSON metadata -8. **发布评论** - 在 PR 中发布结果 - -## 高级配置 - -### 添加代码质量检查 - -```yaml -- name: Run linter - run: | - # Python: pylint, flake8 - pip install pylint - pylint src/ - - # Java: checkstyle - mvn checkstyle:check - - # R: lintr - Rscript -e "lintr::lint_package()" -``` - -### 自定义评分规则 - -修改 `grade.py` 的调用参数： - -```yaml -- name: Grade - run: | - python3 ./.autograde/grade.py \ - --junit junit.xml \ - --out grade.json \ - --summary summary.md \ - --bonus bonus.json # 可选的加分项 -``` - -### 多个测试套件 - -```yaml -- name: Run public tests - run: | - pytest tests_public/ --junit-xml=public.xml - -- name: Run hidden tests - run: | - pytest tests_hidden/ --junit-xml=hidden.xml - -- name: Merge test results - run: | - python3 ./.autograde/merge_junit.py public.xml hidden.xml -o junit.xml -``` - -## 故障排查 - -### 测试无法运行 -- 检查测试目录路径是否正确 -- 确认依赖是否正确安装 -- 查看 Actions 日志中的错误信息 - -### JUnit XML 未生成 -- Python: 确保 pytest 命令包含 `--junit-xml` -- Java: 检查 Surefire 插件配置 -- R: 确认 testthat >= 3.0.0 - -### 元数据为空 -- 检查 `grade.json` 是否生成 -- 确认 `LANGUAGE` 环境变量设置正确 -- 查看 `create_minimal_metadata.py` 的输出 - -## 相关文档 - -- [运行测试脚本](../run_tests.py) - 通用测试运行器 -- [评分脚本](../grade.py) - JUnit XML 解析和评分 -- [元数据生成](../create_minimal_metadata.py) - JSON 元数据 -- [示例](../../examples/) - 各语言的完整示例 - ---- - -最后更新: 2025-11-13 - diff --git a/.autograde/workflow_templates/java.yml b/.autograde/workflow_templates/java.yml deleted file mode 100644 index 3890e01..0000000 --- a/.autograde/workflow_templates/java.yml +++ /dev/null @@ -1,200 +0,0 @@ -name: autograde-java - -on: - push: - branches: - - main - workflow_dispatch: - -permissions: - contents: read - pull-requests: write - -jobs: - java: - runs-on: docker - container: - image: gradle:9.0-jdk21 - options: --user root - timeout-minutes: 20 - - steps: - - name: Install dependencies (CN mirror) - run: | - set -e - # 替换 Debian/Ubuntu 源为腾讯云镜像 - for f in /etc/apt/sources.list /etc/apt/sources.list.d/*.list /etc/apt/sources.list.d/*.sources; do - [ -f "$f" ] || continue - sed -i -E 's|https?://deb.debian.org|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://security.debian.org|http://mirrors.cloud.tencent.com/debian-security|g' "$f" || true - sed -i -E 's|https?://archive.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://ports.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - done - apt-get -o Acquire::Check-Valid-Until=false -o Acquire::AllowInsecureRepositories=true update -y - DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends git ca-certificates python3 python3-pip nodejs rsync - pip3 install --break-system-packages python-dotenv requests -i https://mirrors.cloud.tencent.com/pypi/simple - rm -rf /var/lib/apt/lists/* - - - name: Checkout code - uses: actions/checkout@v3 - with: - fetch-depth: 1 - - - name: Fix permissions - run: | - # Ensure workspace is owned by current user - chown -R $(whoami):$(whoami) ${{ github.workspace }} || true - - - name: Fetch hidden tests (if available) - working-directory: ${{ github.workspace }} - env: - EXTERNAL_GITEA_HOST: ${{ secrets.EXTERNAL_GITEA_HOST }} - run: | - set -e - - TESTS_USERNAME="${RUNNER_TESTS_USERNAME:-}" - TESTS_TOKEN="${RUNNER_TESTS_TOKEN:-}" - - if [ -z "$TESTS_TOKEN" ] || [ -z "$TESTS_USERNAME" ]; then - echo "Warning: RUNNER_TESTS_USERNAME / RUNNER_TESTS_TOKEN not set, skipping private tests" - exit 0 - fi - - # Resolve Gitea Host - if [ -n "$EXTERNAL_GITEA_HOST" ]; then - HOST="$EXTERNAL_GITEA_HOST" - elif [ -n "$GITEA_ROOT_URL" ]; then - HOST=$(echo "$GITEA_ROOT_URL" | sed 's|https\?://||' | sed 's|/$||') - else - HOST=$(echo "${{ github.server_url }}" | sed 's|https\?://||' | cut -d'/' -f1) - fi - - echo "📥 Fetching private tests repository..." - echo " Gitea host: $HOST" - - # Infer organization and assignment ID from repository name - ORG=$(echo "${{ github.repository }}" | cut -d'/' -f1) - REPO_NAME=$(echo "${{ github.repository }}" | cut -d'/' -f2) - - # Extract assignment ID from repo name (e.g., hw2-stu_xxx -> hw2, hw2-template -> hw2) - if echo "$REPO_NAME" | grep -q -- '-stu_'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-stu_.*//') - elif echo "$REPO_NAME" | grep -q -- '-template'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-template.*//') - else - ASSIGNMENT_ID="hw1" # fallback - fi - - echo " Organization: $ORG" - echo " Assignment ID: $ASSIGNMENT_ID" - - # Clone private test repository - AUTH_URL="http://${TESTS_USERNAME}:${TESTS_TOKEN}@${HOST}/${ORG}/${ASSIGNMENT_ID}-tests.git" - - if ! git -c http.sslVerify=false clone --depth=1 "$AUTH_URL" _priv_tests 2>&1; then - echo "❌ Failed to clone ${ASSIGNMENT_ID}-tests repository!" - exit 1 - fi - - # Verify test directory exists - if [ ! -d "_priv_tests/java" ]; then - echo "❌ java/ directory not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - if [ ! -d "_priv_tests/java/src/test" ]; then - echo "❌ java/src/test/ not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - # Copy tests to src/test/ - rsync -a _priv_tests/java/src/test/ src/test/ - echo "✅ Private tests copied: _priv_tests/java/src/test/ → src/test/" - - - name: Run tests using Gradle - working-directory: ${{ github.workspace }} - env: - LANGUAGE: java - run: | - gradle test --no-daemon || true - - - name: Extract test results - working-directory: ${{ github.workspace }} - run: | - # Find JUnit XML report - XML_REPORT=$(find build/test-results/test -name "TEST-*.xml" | head -n 1) - if [ -n "$XML_REPORT" ]; then - cp "$XML_REPORT" junit.xml - echo "✅ Found JUnit report: $XML_REPORT" - else - echo "⚠️ No JUnit report found!" - touch junit.xml - fi - - - name: Grade - working-directory: ${{ github.workspace }} - env: - LANGUAGE: java - run: | - python3 ./.autograde/grade.py --junit junit.xml --out grade.json --summary summary.md - - - name: Prepare artifacts - working-directory: ${{ github.workspace }} - run: | - mkdir -p artifacts - cp junit.xml summary.md grade.json artifacts/ 2>/dev/null || true - - - name: Create grade metadata - working-directory: ${{ github.workspace }} - env: - LANGUAGE: java - REPO: ${{ github.repository }} - run: | - if [ ! -f grade.json ]; then - echo "⚠️ grade.json not found, skipping metadata creation" - exit 0 - fi - - # 生成 JSON 元数据 - if [ -f ./.autograde/create_grade_metadata.py ]; then - python3 ./.autograde/create_grade_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_grade_metadata.py)" - elif [ -f ./.autograde/create_minimal_metadata.py ]; then - export GRADE_TYPE=programming - python3 ./.autograde/create_minimal_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_minimal_metadata.py)" - else - echo "⚠️ No metadata creation script found, skipping" - echo "{}" > metadata.json - fi - - - name: Upload metadata (teacher only) - if: env.RUNNER_METADATA_REPO != '' && env.RUNNER_METADATA_TOKEN != '' - working-directory: ${{ github.workspace }} - shell: bash - env: - METADATA_REPO: ${{ env.RUNNER_METADATA_REPO }} - METADATA_TOKEN: ${{ env.RUNNER_METADATA_TOKEN }} - METADATA_BRANCH: ${{ env.RUNNER_METADATA_BRANCH }} - STUDENT_REPO: ${{ github.repository }} - RUN_ID: ${{ github.run_id }} - COMMIT_SHA: ${{ github.sha }} - SERVER_URL: ${{ github.server_url }} - run: | - set -e - if [ ! -f metadata.json ]; then - echo "No metadata.json found, skip uploading." - exit 0 - fi - - python3 ./.autograde/upload_metadata.py \ - --metadata-file metadata.json \ - --metadata-repo "${METADATA_REPO}" \ - --branch "${METADATA_BRANCH:-main}" \ - --student-repo "${STUDENT_REPO}" \ - --run-id "${RUN_ID}" \ - --commit-sha "${COMMIT_SHA}" \ - --workflow grade \ - --server-url "${SERVER_URL}" \ - --external-host "${EXTERNAL_GITEA_HOST}" - rm -f metadata.json diff --git a/.autograde/workflow_templates/python.yml b/.autograde/workflow_templates/python.yml deleted file mode 100644 index a92d546..0000000 --- a/.autograde/workflow_templates/python.yml +++ /dev/null @@ -1,206 +0,0 @@ -name: autograde-python - -on: - push: - branches: - - main - workflow_dispatch: - -permissions: - contents: read - pull-requests: write - -jobs: - python: - runs-on: docker - container: python:3.11 - timeout-minutes: 15 - - steps: - - name: Install dependencies (CN mirror) - run: | - set -e - # 替换 Debian/Ubuntu 源为腾讯云镜像 - for f in /etc/apt/sources.list /etc/apt/sources.list.d/*.list /etc/apt/sources.list.d/*.sources; do - [ -f "$f" ] || continue - sed -i -E 's|https?://deb.debian.org|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://security.debian.org|http://mirrors.cloud.tencent.com/debian-security|g' "$f" || true - sed -i -E 's|https?://archive.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://ports.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - done - apt-get -o Acquire::Check-Valid-Until=false -o Acquire::AllowInsecureRepositories=true update -y - DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends git ca-certificates python3 python3-pip nodejs rsync - rm -rf /var/lib/apt/lists/* - - - name: Checkout code - uses: actions/checkout@v3 - with: - fetch-depth: 1 - - - name: Fix permissions - run: | - # Ensure workspace is owned by current user - chown -R $(whoami):$(whoami) ${{ github.workspace }} || true - - - name: Install Python deps - working-directory: ${{ github.workspace }} - run: | - # 使用腾讯云镜像源加速 - python -m pip install -U pip -i https://mirrors.cloud.tencent.com/pypi/simple - if [ -f requirements.txt ]; then pip install -r requirements.txt -i https://mirrors.cloud.tencent.com/pypi/simple; fi - if [ -f pyproject.toml ]; then pip install . -i https://mirrors.cloud.tencent.com/pypi/simple; fi - pip install pytest pytest-cov junit-xml python-dotenv requests -i https://mirrors.cloud.tencent.com/pypi/simple - - - name: Fetch private tests - working-directory: ${{ github.workspace }} - env: - EXTERNAL_GITEA_HOST: ${{ secrets.EXTERNAL_GITEA_HOST }} - run: | - set -e - - TESTS_USERNAME="${RUNNER_TESTS_USERNAME:-}" - TESTS_TOKEN="${RUNNER_TESTS_TOKEN:-}" - - if [ -z "$TESTS_TOKEN" ] || [ -z "$TESTS_USERNAME" ]; then - echo "❌ RUNNER_TESTS_USERNAME / RUNNER_TESTS_TOKEN 未配置!" - echo "测试必须从私有的 tests 仓库获取" - exit 1 - fi - - # Resolve Gitea Host - if [ -n "$EXTERNAL_GITEA_HOST" ]; then - HOST="$EXTERNAL_GITEA_HOST" - elif [ -n "$GITEA_ROOT_URL" ]; then - HOST=$(echo "$GITEA_ROOT_URL" | sed 's|https\?://||' | sed 's|/$||') - else - HOST=$(echo "${{ github.server_url }}" | sed 's|https\?://||' | cut -d'/' -f1) - fi - - echo "📥 Fetching private tests repository..." - echo " Gitea host: $HOST" - - # Infer organization and assignment ID from repository name - ORG=$(echo "${{ github.repository }}" | cut -d'/' -f1) - REPO_NAME=$(echo "${{ github.repository }}" | cut -d'/' -f2) - - # Extract assignment ID from repo name (e.g., hw1-stu_xxx -> hw1, hw1-template -> hw1) - if echo "$REPO_NAME" | grep -q -- '-stu_'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-stu_.*//') - elif echo "$REPO_NAME" | grep -q -- '-template'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-template.*//') - else - ASSIGNMENT_ID="hw1" # fallback - fi - - echo " Organization: $ORG" - echo " Assignment ID: $ASSIGNMENT_ID" - - AUTH_URL="http://${TESTS_USERNAME}:${TESTS_TOKEN}@${HOST}/${ORG}/${ASSIGNMENT_ID}-tests.git" - if ! git -c http.sslVerify=false clone --depth=1 "$AUTH_URL" _priv_tests 2>&1; then - echo "❌ Failed to clone ${ASSIGNMENT_ID}-tests repository!" - exit 1 - fi - - # 验证测试目录存在 - if [ ! -d "_priv_tests/python" ]; then - echo "❌ python/ directory not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - if [ ! -d "_priv_tests/python/tests" ]; then - echo "❌ python/tests/ not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - # 复制测试到 tests/ - mkdir -p tests - rsync -a _priv_tests/python/tests/ tests/ - echo "✅ Tests copied: _priv_tests/python/tests/ → tests/" - - # 复制数据文件（如果存在） - if [ -d "_priv_tests/python/data" ]; then - mkdir -p tests/data - rsync -a _priv_tests/python/data/ tests/data/ - echo "✅ Data files copied: _priv_tests/python/data/ → tests/data/" - fi - - # 验证测试文件 - if [ -z "$(find tests -name 'test_*.py' 2>/dev/null)" ]; then - echo "❌ No test files found in tests/ directory!" - exit 1 - fi - - echo "✅ Test suite ready:" - find tests -name 'test_*.py' - - - name: Run tests - working-directory: ${{ github.workspace }} - run: | - # 设置随机种子 - export PYTHONHASHSEED=2025 - pytest -q --maxfail=0 --junitxml=junit.xml --tb=short || true - - - name: Grade - working-directory: ${{ github.workspace }} - run: | - python ./.autograde/grade.py --junit junit.xml --out grade.json --summary summary.md - - - name: Prepare artifacts - working-directory: ${{ github.workspace }} - run: | - mkdir -p artifacts - cp junit.xml summary.md grade.json artifacts/ 2>/dev/null || true - - - name: Create grade metadata - working-directory: ${{ github.workspace }} - env: - REPO: ${{ github.repository }} - run: | - if [ ! -f grade.json ]; then - echo "⚠️ grade.json not found, skipping metadata creation" - exit 0 - fi - - # 生成 JSON 元数据 - if [ -f ./.autograde/create_grade_metadata.py ]; then - python3 ./.autograde/create_grade_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_grade_metadata.py)" - elif [ -f ./.autograde/create_minimal_metadata.py ]; then - export GRADE_TYPE=programming - python3 ./.autograde/create_minimal_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_minimal_metadata.py)" - else - echo "⚠️ No metadata creation script found, skipping" - echo "{}" > metadata.json - fi - - - name: Upload metadata (teacher only) - if: env.RUNNER_METADATA_REPO != '' && env.RUNNER_METADATA_TOKEN != '' - working-directory: ${{ github.workspace }} - shell: bash - env: - METADATA_REPO: ${{ env.RUNNER_METADATA_REPO }} - METADATA_TOKEN: ${{ env.RUNNER_METADATA_TOKEN }} - METADATA_BRANCH: ${{ env.RUNNER_METADATA_BRANCH }} - STUDENT_REPO: ${{ github.repository }} - RUN_ID: ${{ github.run_id }} - COMMIT_SHA: ${{ github.sha }} - SERVER_URL: ${{ github.server_url }} - run: | - set -e - if [ ! -f metadata.json ]; then - echo "No metadata.json found, skip uploading." - exit 0 - fi - - python ./.autograde/upload_metadata.py \ - --metadata-file metadata.json \ - --metadata-repo "${METADATA_REPO}" \ - --branch "${METADATA_BRANCH:-main}" \ - --student-repo "${STUDENT_REPO}" \ - --run-id "${RUN_ID}" \ - --commit-sha "${COMMIT_SHA}" \ - --workflow grade \ - --server-url "${SERVER_URL}" \ - --external-host "${EXTERNAL_GITEA_HOST}" - rm -f metadata.json diff --git a/.autograde/workflow_templates/r.yml b/.autograde/workflow_templates/r.yml deleted file mode 100644 index 52db86d..0000000 --- a/.autograde/workflow_templates/r.yml +++ /dev/null @@ -1,200 +0,0 @@ -name: autograde-r - -on: - push: - branches: - - main - workflow_dispatch: - -permissions: - contents: read - pull-requests: write - -jobs: - r: - runs-on: docker - container: r-base:4.3.1 - timeout-minutes: 15 - - steps: - - name: Install dependencies (CN mirror) - run: | - set -e - # 替换 Debian/Ubuntu 源为腾讯云镜像 - for f in /etc/apt/sources.list /etc/apt/sources.list.d/*.list /etc/apt/sources.list.d/*.sources; do - [ -f "$f" ] || continue - sed -i -E 's|https?://deb.debian.org|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://security.debian.org|http://mirrors.cloud.tencent.com/debian-security|g' "$f" || true - sed -i -E 's|https?://archive.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - sed -i -E 's|https?://ports.ubuntu.com|http://mirrors.cloud.tencent.com|g' "$f" || true - done - apt-get -o Acquire::Check-Valid-Until=false -o Acquire::AllowInsecureRepositories=true update -y - DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends git ca-certificates python3 python3-pip nodejs rsync libcurl4-openssl-dev libssl-dev libxml2-dev - pip3 install --break-system-packages python-dotenv requests -i https://mirrors.cloud.tencent.com/pypi/simple - rm -rf /var/lib/apt/lists/* - - - name: Configure CRAN Mirror - run: | - echo 'options(repos = c(CRAN = "https://mirrors.tuna.tsinghua.edu.cn/CRAN/"))' >> ~/.Rprofile - - - name: Install R packages - run: | - Rscript -e 'install.packages(c("testthat", "covr", "xml2"))' - - - name: Checkout code - uses: actions/checkout@v3 - with: - fetch-depth: 1 - - - name: Fix permissions - run: | - # Ensure workspace is owned by current user - chown -R $(whoami):$(whoami) ${{ github.workspace }} || true - - - name: Fetch private tests - working-directory: ${{ github.workspace }} - env: - EXTERNAL_GITEA_HOST: ${{ secrets.EXTERNAL_GITEA_HOST }} - run: | - set -e - - TESTS_USERNAME="${RUNNER_TESTS_USERNAME:-}" - TESTS_TOKEN="${RUNNER_TESTS_TOKEN:-}" - - if [ -z "$TESTS_TOKEN" ] || [ -z "$TESTS_USERNAME" ]; then - echo "❌ RUNNER_TESTS_USERNAME / RUNNER_TESTS_TOKEN 未配置!" - echo "测试必须从私有的 tests 仓库获取" - exit 1 - fi - - # Resolve Gitea Host - if [ -n "$EXTERNAL_GITEA_HOST" ]; then - HOST="$EXTERNAL_GITEA_HOST" - elif [ -n "$GITEA_ROOT_URL" ]; then - HOST=$(echo "$GITEA_ROOT_URL" | sed 's|https\?://||' | sed 's|/$||') - else - HOST=$(echo "${{ github.server_url }}" | sed 's|https\?://||' | cut -d'/' -f1) - fi - - echo "📥 Fetching private tests repository..." - echo " Gitea host: $HOST" - - # Infer organization and assignment ID from repository name - ORG=$(echo "${{ github.repository }}" | cut -d'/' -f1) - REPO_NAME=$(echo "${{ github.repository }}" | cut -d'/' -f2) - - # Extract assignment ID from repo name (e.g., hw1-stu_xxx -> hw1, hw1-template -> hw1) - if echo "$REPO_NAME" | grep -q -- '-stu_'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-stu_.*//') - elif echo "$REPO_NAME" | grep -q -- '-template'; then - ASSIGNMENT_ID=$(echo "$REPO_NAME" | sed 's/-template.*//') - else - ASSIGNMENT_ID="hw1" # fallback - fi - - echo " Organization: $ORG" - echo " Assignment ID: $ASSIGNMENT_ID" - - AUTH_URL="http://${TESTS_USERNAME}:${TESTS_TOKEN}@${HOST}/${ORG}/${ASSIGNMENT_ID}-tests.git" - if ! git -c http.sslVerify=false clone --depth=1 "$AUTH_URL" _priv_tests 2>&1; then - echo "❌ Failed to clone ${ASSIGNMENT_ID}-tests repository!" - exit 1 - fi - - # 验证测试目录存在 - if [ ! -d "_priv_tests/r" ]; then - echo "❌ r/ directory not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - if [ ! -d "_priv_tests/r/tests" ]; then - echo "❌ r/tests/ not found in ${ASSIGNMENT_ID}-tests!" - exit 1 - fi - - # 复制测试到 tests/ - mkdir -p tests - rsync -a _priv_tests/r/tests/ tests/ - echo "✅ Tests copied: _priv_tests/r/tests/ → tests/" - - # 验证测试文件 - if [ -z "$(find tests -name 'test_*.R' 2>/dev/null)" ]; then - echo "❌ No test files found in tests/ directory!" - exit 1 - fi - - echo "✅ Test suite ready:" - find tests -name 'test_*.R' - - - name: Run tests - working-directory: ${{ github.workspace }} - run: | - Rscript -e 'library(testthat); test_dir("tests", reporter = JunitReporter$new(file = "junit.xml"))' || true - - - name: Grade - working-directory: ${{ github.workspace }} - env: - LANGUAGE: r - run: | - python3 ./.autograde/grade.py --junit junit.xml --out grade.json --summary summary.md - - - name: Prepare artifacts - working-directory: ${{ github.workspace }} - run: | - mkdir -p artifacts - cp junit.xml summary.md grade.json artifacts/ 2>/dev/null || true - - - name: Create grade metadata - working-directory: ${{ github.workspace }} - env: - LANGUAGE: r - REPO: ${{ github.repository }} - run: | - if [ ! -f grade.json ]; then - echo "⚠️ grade.json not found, skipping metadata creation" - exit 0 - fi - - # 生成 JSON 元数据 - if [ -f ./.autograde/create_grade_metadata.py ]; then - python3 ./.autograde/create_grade_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_grade_metadata.py)" - elif [ -f ./.autograde/create_minimal_metadata.py ]; then - export GRADE_TYPE=programming - python3 ./.autograde/create_minimal_metadata.py > metadata.json || echo "{}" > metadata.json - echo "✅ Grade metadata created (using create_minimal_metadata.py)" - else - echo "⚠️ No metadata creation script found, skipping" - echo "{}" > metadata.json - fi - - - name: Upload metadata (teacher only) - if: env.RUNNER_METADATA_REPO != '' && env.RUNNER_METADATA_TOKEN != '' - working-directory: ${{ github.workspace }} - shell: bash - env: - METADATA_REPO: ${{ env.RUNNER_METADATA_REPO }} - METADATA_TOKEN: ${{ env.RUNNER_METADATA_TOKEN }} - METADATA_BRANCH: ${{ env.RUNNER_METADATA_BRANCH }} - STUDENT_REPO: ${{ github.repository }} - RUN_ID: ${{ github.run_id }} - COMMIT_SHA: ${{ github.sha }} - SERVER_URL: ${{ github.server_url }} - run: | - set -e - if [ ! -f metadata.json ]; then - echo "No metadata.json found, skip uploading." - exit 0 - fi - - python3 ./.autograde/upload_metadata.py \ - --metadata-file metadata.json \ - --metadata-repo "${METADATA_REPO}" \ - --branch "${METADATA_BRANCH:-main}" \ - --student-repo "${STUDENT_REPO}" \ - --run-id "${RUN_ID}" \ - --commit-sha "${COMMIT_SHA}" \ - --workflow grade \ - --server-url "${SERVER_URL}" \ - --external-host "${EXTERNAL_GITEA_HOST}" - rm -f metadata.json diff --git a/.gitea/workflows/autograde.yml b/.gitea/workflows/autograde.yml index 69b6ce3..66d6b42 100644 --- a/.gitea/workflows/autograde.yml +++ b/.gitea/workflows/autograde.yml @@ -72,7 +72,7 @@ jobs: - name: Fix permissions run: chown -R $(whoami):$(whoami) ${{ github.workspace }} || true - - name: Fetch hidden tests + - name: Fetch hidden tests and grading scripts working-directory: ${{ github.workspace }} env: EXTERNAL_GITEA_HOST: ${{ secrets.EXTERNAL_GITEA_HOST }} @@ -83,8 +83,9 @@ jobs: TESTS_TOKEN="${RUNNER_TESTS_TOKEN:-}" if [ -z "$TESTS_TOKEN" ] || [ -z "$TESTS_USERNAME" ]; then - echo "Warning: RUNNER_TESTS_USERNAME / RUNNER_TESTS_TOKEN not set, skipping private tests" - exit 0 + echo "❌ RUNNER_TESTS_USERNAME / RUNNER_TESTS_TOKEN not set!" + echo "Cannot fetch grading scripts - aborting." + exit 1 fi # Resolve Gitea Host @@ -108,7 +109,7 @@ jobs: ASSIGNMENT_ID="final-vibevault" fi - echo "📥 Fetching private tests from ${ORG}/${ASSIGNMENT_ID}-tests..." + echo "📥 Fetching tests and grading scripts from ${ORG}/${ASSIGNMENT_ID}-tests..." AUTH_URL="http://${TESTS_USERNAME}:${TESTS_TOKEN}@${HOST}/${ORG}/${ASSIGNMENT_ID}-tests.git" @@ -117,6 +118,19 @@ jobs: exit 1 fi + # ===== Copy grading scripts (from tests repo, cannot be modified by students) ===== + if [ -d "_priv_tests/autograde" ]; then + # Remove any local .autograde (prevent student tampering) + rm -rf .autograde + mkdir -p .autograde + cp _priv_tests/autograde/*.py .autograde/ + cp _priv_tests/autograde/*.sh .autograde/ 2>/dev/null || true + echo "✅ Grading scripts copied from tests repo" + else + echo "❌ No autograde directory in tests repo!" + exit 1 + fi + # Copy Java tests if [ -d "_priv_tests/java/src/test" ]; then rsync -a _priv_tests/java/src/test/ src/test/ @@ -135,6 +149,9 @@ jobs: cp _priv_tests/llm/*.json .llm_rubrics/ 2>/dev/null || true echo "✅ LLM rubrics copied" fi + + # Cleanup + rm -rf _priv_tests - name: Run tests working-directory: ${{ github.workspace }}