初始化课评系统仓库：包含规则配置、学生档案、课程教案、班级汇总
This commit is contained in:
qiuyan
311
src/evaluation_validator.py
Normal file
311
src/evaluation_validator.py
Normal file
@@ -0,0 +1,311 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
课评质量自动验证脚本
|
||||
用于检查生成的课评是否符合规范
|
||||
|
||||
使用方法:
|
||||
python evaluation_validator.py <课评文件路径>
|
||||
python evaluation_validator.py --batch <班级汇总文件路径>
|
||||
python evaluation_validator.py --student <学生历史课评文件路径>
|
||||
"""
|
||||
|
||||
import sys
|
||||
import io
|
||||
import re
|
||||
import argparse
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
|
||||
# 设置UTF-8输出编码
|
||||
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
||||
sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8')
|
||||
|
||||
# ============ 配置项 ============
|
||||
|
||||
# 字数范围配置（与规则文件保持一致）
|
||||
MIN_LENGTH = 180
|
||||
MAX_LENGTH = 350
|
||||
|
||||
# 禁用词汇列表
|
||||
FORBIDDEN_WORDS = [
|
||||
"宝贝", "小天才", "最棒", "无敌", "超级厉害", "完美",
|
||||
"在今天的课堂上", "通过本次活动",
|
||||
"比其他小朋友", "补课", "补课上", "来补课", "本次补课",
|
||||
"临时加入", "从其他班级过来"
|
||||
]
|
||||
|
||||
# 必须包含的模块关键词（至少包含其中几类）
|
||||
REQUIRED_MODULES = {
|
||||
"课程知识点": ["学习了", "认识了", "探索了", "了解了"],
|
||||
"掌握程度": ["完成", "掌握", "理解", "尝试", "独立"],
|
||||
"课后建议": ["在家", "可以", "建议", "巩固"]
|
||||
}
|
||||
|
||||
# Emoji检查配置
|
||||
MIN_EMOJI = 3
|
||||
MAX_EMOJI = 5
|
||||
|
||||
# ============ 核心验证类 ============
|
||||
|
||||
class EvaluationValidator:
|
||||
def __init__(self, text: str, student_name: str = ""):
|
||||
self.text = text
|
||||
self.student_name = student_name
|
||||
self.errors = []
|
||||
self.warnings = []
|
||||
self.stats = {}
|
||||
|
||||
def validate_all(self) -> dict:
|
||||
"""执行所有验证检查"""
|
||||
self.check_length()
|
||||
self.check_forbidden_words()
|
||||
self.check_emoji_count()
|
||||
self.check_modules()
|
||||
self.check_name_usage()
|
||||
self.check_week_number()
|
||||
self.check_paragraph_structure()
|
||||
|
||||
return {
|
||||
"status": "通过" if not self.errors else "未通过",
|
||||
"errors": self.errors,
|
||||
"warnings": self.warnings,
|
||||
"stats": self.stats
|
||||
}
|
||||
|
||||
def check_length(self):
|
||||
"""检查字数是否在弹性范围内"""
|
||||
# 计算中文字符数（不含空格、换行、标点）
|
||||
chinese_chars = len(re.findall(r'[\u4e00-\u9fff]', self.text))
|
||||
# 计算总字符数（含英文单词）
|
||||
total_chars = len(self.text.replace(' ', '').replace('\n', ''))
|
||||
|
||||
self.stats["中文字数"] = chinese_chars
|
||||
self.stats["总字符数"] = total_chars
|
||||
|
||||
if chinese_chars < MIN_LENGTH:
|
||||
self.errors.append(f"字数不足：当前{chinese_chars}字，最少要求{MIN_LENGTH}字")
|
||||
elif chinese_chars > MAX_LENGTH:
|
||||
self.warnings.append(f"字数偏多：当前{chinese_chars}字，建议控制在{MAX_LENGTH}字以内")
|
||||
else:
|
||||
self.stats["字数检查"] = f"✅ 通过（{chinese_chars}字）"
|
||||
|
||||
def check_forbidden_words(self):
|
||||
"""检查是否包含禁用词汇"""
|
||||
found = []
|
||||
for word in FORBIDDEN_WORDS:
|
||||
if word in self.text:
|
||||
found.append(word)
|
||||
|
||||
if found:
|
||||
self.errors.append(f"包含禁用词汇：{', '.join(found)}")
|
||||
else:
|
||||
self.stats["禁用词检查"] = "✅ 通过"
|
||||
|
||||
def check_emoji_count(self):
|
||||
"""检查Emoji数量"""
|
||||
# 只匹配真正的Emoji字符（排除Markdown符号如✓、✅等）
|
||||
# 匹配Unicode Emoji范围
|
||||
emojis = re.findall(r'[\U0001F300-\U0001F9FF]', self.text)
|
||||
emoji_count = len(emojis)
|
||||
self.stats["Emoji数量"] = emoji_count
|
||||
|
||||
if emoji_count < MIN_EMOJI:
|
||||
self.warnings.append(f"Emoji较少：当前{emoji_count}个，建议至少{MIN_EMOJI}个")
|
||||
elif emoji_count > MAX_EMOJI:
|
||||
self.warnings.append(f"Emoji较多：当前{emoji_count}个，建议不超过{MAX_EMOJI}个")
|
||||
else:
|
||||
self.stats["Emoji检查"] = f"✅ 通过（{emoji_count}个）"
|
||||
|
||||
def check_modules(self):
|
||||
"""检查是否包含必要的模块内容"""
|
||||
missing_modules = []
|
||||
for module_name, keywords in REQUIRED_MODULES.items():
|
||||
if not any(keyword in self.text for keyword in keywords):
|
||||
missing_modules.append(module_name)
|
||||
|
||||
if missing_modules:
|
||||
self.warnings.append(f"可能缺少以下模块：{', '.join(missing_modules)}")
|
||||
else:
|
||||
self.stats["模块检查"] = "✅ 通过"
|
||||
|
||||
def check_name_usage(self):
|
||||
"""检查学生称呼使用是否正确"""
|
||||
if not self.student_name:
|
||||
return
|
||||
|
||||
# 检查是否使用了全名（应该使用小名/去姓/叠字）
|
||||
if len(self.student_name) >= 3 and self.student_name in self.text:
|
||||
self.warnings.append(f"可能使用了全名'{self.student_name}'，建议使用小名或去姓称呼")
|
||||
|
||||
def check_week_number(self):
|
||||
"""检查正文中是否出现了周数信息"""
|
||||
week_patterns = [r'第\d+周', r'本周第\d+节', r'第\d+节课']
|
||||
found = []
|
||||
for pattern in week_patterns:
|
||||
matches = re.findall(pattern, self.text)
|
||||
found.extend(matches)
|
||||
|
||||
if found:
|
||||
self.errors.append(f"课评正文禁止出现周数：{', '.join(found)}")
|
||||
else:
|
||||
self.stats["周数检查"] = "✅ 通过"
|
||||
|
||||
def check_paragraph_structure(self):
|
||||
"""检查段落结构"""
|
||||
paragraphs = [p.strip() for p in self.text.split('\n\n') if p.strip()]
|
||||
|
||||
if len(paragraphs) != 3:
|
||||
self.warnings.append(f"段落数建议为3段，当前{len(paragraphs)}段")
|
||||
else:
|
||||
self.stats["段落检查"] = "✅ 通过（3段）"
|
||||
|
||||
self.stats["段落数"] = len(paragraphs)
|
||||
|
||||
|
||||
# ============ 文件解析函数 ============
|
||||
|
||||
def parse_class_summary(file_path: str) -> list:
|
||||
"""解析班级周汇总文件，提取各学生课评"""
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
evaluations = []
|
||||
|
||||
# 匹配学生课评区块
|
||||
pattern = r'###\s*(.+?)\n\n(.+?)(?=\n###|\Z)'
|
||||
matches = re.findall(pattern, content, re.DOTALL)
|
||||
|
||||
for name_section, eval_text in matches:
|
||||
# 提取学生姓名（去掉括号内容）
|
||||
name = name_section.split('（')[0].strip()
|
||||
evaluations.append({
|
||||
"name": name,
|
||||
"text": eval_text.strip()
|
||||
})
|
||||
|
||||
return evaluations
|
||||
|
||||
|
||||
def parse_student_history(file_path: str) -> list:
|
||||
"""解析学生历史课评文件，提取各条课评"""
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
evaluations = []
|
||||
|
||||
# 匹配课评记录
|
||||
pattern = r'###\s*(\d{4}-\d{2}-\d{2})\s*\|\s*课程代码：(.+?)\n\n\*\*课评内容\*\*：\n\n(.+?)(?=\n\*\*能力评估\*\*|\Z)'
|
||||
matches = re.findall(pattern, content, re.DOTALL)
|
||||
|
||||
for date, course_code, eval_text in matches:
|
||||
evaluations.append({
|
||||
"date": date,
|
||||
"course": course_code,
|
||||
"text": eval_text.strip()
|
||||
})
|
||||
|
||||
return evaluations
|
||||
|
||||
|
||||
# ============ 输出格式化 ============
|
||||
|
||||
def print_result(result: dict, identifier: str = ""):
|
||||
"""打印验证结果"""
|
||||
print(f"\n{'='*60}")
|
||||
if identifier:
|
||||
print(f"📋 验证对象：{identifier}")
|
||||
print(f"🎯 验证状态：{result['status']}")
|
||||
print(f"{'='*60}")
|
||||
|
||||
if result['stats']:
|
||||
print("\n📊 统计信息：")
|
||||
for key, value in result['stats'].items():
|
||||
print(f" {key}: {value}")
|
||||
|
||||
if result['errors']:
|
||||
print("\n❌ 错误（必须修复）：")
|
||||
for error in result['errors']:
|
||||
print(f" • {error}")
|
||||
|
||||
if result['warnings']:
|
||||
print("\n⚠️ 警告（建议优化）：")
|
||||
for warning in result['warnings']:
|
||||
print(f" • {warning}")
|
||||
|
||||
if not result['errors'] and not result['warnings']:
|
||||
print("\n✅ 所有检查项通过！")
|
||||
|
||||
print(f"{'='*60}\n")
|
||||
|
||||
|
||||
# ============ 主函数 ============
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='课评质量自动验证工具')
|
||||
parser.add_argument('file', help='要验证的文件路径')
|
||||
parser.add_argument('--batch', action='store_true', help='批量验证班级汇总文件')
|
||||
parser.add_argument('--student', action='store_true', help='验证学生历史课评文件')
|
||||
parser.add_argument('--text', action='store_true', help='直接验证文本内容')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.text:
|
||||
# 直接验证文本
|
||||
with open(args.file, 'r', encoding='utf-8') as f:
|
||||
text = f.read()
|
||||
validator = EvaluationValidator(text)
|
||||
result = validator.validate_all()
|
||||
print_result(result, "文本内容")
|
||||
|
||||
elif args.batch:
|
||||
# 批量验证班级汇总
|
||||
print(f"📁 正在解析班级汇总文件：{args.file}")
|
||||
evaluations = parse_class_summary(args.file)
|
||||
print(f"找到 {len(evaluations)} 条课评记录\n")
|
||||
|
||||
all_passed = True
|
||||
for eval_data in evaluations:
|
||||
validator = EvaluationValidator(eval_data['text'], eval_data['name'])
|
||||
result = validator.validate_all()
|
||||
print_result(result, f"学生：{eval_data['name']}")
|
||||
if result['status'] != '通过':
|
||||
all_passed = False
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"📊 批量验证完成：{len(evaluations)}条课评")
|
||||
print(f"🎯 总体状态：{'✅ 全部通过' if all_passed else '❌ 存在未通过项'}")
|
||||
print(f"{'='*60}")
|
||||
|
||||
elif args.student:
|
||||
# 验证学生历史课评
|
||||
print(f"📁 正在解析学生历史课评：{args.file}")
|
||||
evaluations = parse_student_history(args.file)
|
||||
print(f"找到 {len(evaluations)} 条历史记录\n")
|
||||
|
||||
for eval_data in evaluations:
|
||||
validator = EvaluationValidator(eval_data['text'])
|
||||
result = validator.validate_all()
|
||||
print_result(result, f"日期：{eval_data['date']} | 课程：{eval_data['course']}")
|
||||
|
||||
else:
|
||||
# 默认：尝试自动识别文件类型
|
||||
with open(args.file, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
if '班级周汇总' in content or '学生课评列表' in content:
|
||||
print("🔍 自动识别为：班级汇总文件")
|
||||
evaluations = parse_class_summary(args.file)
|
||||
for eval_data in evaluations:
|
||||
validator = EvaluationValidator(eval_data['text'], eval_data['name'])
|
||||
result = validator.validate_all()
|
||||
print_result(result, f"学生：{eval_data['name']}")
|
||||
else:
|
||||
print("🔍 自动识别为：单条课评文本")
|
||||
validator = EvaluationValidator(content)
|
||||
result = validator.validate_all()
|
||||
print_result(result, args.file)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user