123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129 |
- #!/usr/bin/env python3
- """
- 测试修改后的parse_resume_with_qwen函数的字段映射功能
- """
- import os
- import sys
- import logging
- from pathlib import Path
- # 添加项目根目录到Python路径
- project_root = Path(__file__).parent
- sys.path.insert(0, str(project_root))
- # 配置日志
- logging.basicConfig(
- level=logging.INFO,
- format='%(asctime)s - %(levelname)s - %(message)s'
- )
- def test_field_mapping():
- """测试字段映射功能"""
- try:
- # 导入函数
- from app.core.data_parse.parse_resume import parse_resume_with_qwen
-
- # 测试文件路径
- test_file = "方全.pdf"
-
- # 检查文件是否存在
- if not os.path.exists(test_file):
- print(f"错误: 测试文件 {test_file} 不存在")
- return False
-
- print(f"开始测试字段映射功能...")
- print(f"测试文件: {test_file}")
- print(f"文件大小: {os.path.getsize(test_file)} 字节")
-
- # 调用函数
- result = parse_resume_with_qwen(test_file)
-
- # 输出映射结果
- print("\n=== 字段映射结果 ===")
- print(f"姓名(中文): {result.get('name_zh', 'N/A')}")
- print(f"姓名(英文): {result.get('name_en', 'N/A')}")
- print(f"职位(中文): {result.get('title_zh', 'N/A')}")
- print(f"职位(英文): {result.get('title_en', 'N/A')}")
- print(f"公司(中文): {result.get('hotel_zh', 'N/A')}")
- print(f"公司(英文): {result.get('hotel_en', 'N/A')}")
- print(f"手机号码: {result.get('mobile', 'N/A')}")
- print(f"固定电话: {result.get('phone', 'N/A')}")
- print(f"电子邮箱: {result.get('email', 'N/A')}")
- print(f"地址(中文): {result.get('address_zh', 'N/A')}")
- print(f"地址(英文): {result.get('address_en', 'N/A')}")
- print(f"生日: {result.get('birthday', 'N/A')}")
- print(f"年龄: {result.get('age', 'N/A')}")
- print(f"籍贯: {result.get('native_place', 'N/A')}")
- print(f"居住地: {result.get('residence', 'N/A')}")
- print(f"品牌组合: {result.get('brand_group', 'N/A')}")
-
- # 输出职业轨迹
- career_path = result.get('career_path', [])
- if career_path:
- print(f"\n职业轨迹 (共{len(career_path)}条):")
- for i, career in enumerate(career_path, 1):
- print(f" {i}. 日期: {career.get('date', 'N/A')}")
- print(f" 公司: {career.get('hotel_zh', 'N/A')} / {career.get('hotel_en', 'N/A')}")
- print(f" 职位: {career.get('title_zh', 'N/A')} / {career.get('title_en', 'N/A')}")
- else:
- print("\n职业轨迹: 无")
-
- # 输出隶属关系
- affiliation = result.get('affiliation', [])
- if affiliation:
- print(f"\n隶属关系 (共{len(affiliation)}条):")
- for i, aff in enumerate(affiliation, 1):
- print(f" {i}. 公司: {aff.get('company', 'N/A')}")
- print(f" 集团: {aff.get('group', 'N/A')}")
- else:
- print("\n隶属关系: 无")
-
- # 验证字段映射是否正确
- print("\n=== 字段映射验证 ===")
- mapping_verification = {
- 'name_zh': '中文姓名',
- 'name_en': '英文姓名',
- 'title_zh': '中文头衔',
- 'title_en': '英文头衔',
- 'hotel_zh': '中文酒店',
- 'hotel_en': '英文酒店',
- 'mobile': '手机号',
- 'email': '邮箱',
- 'address_zh': '中文工作地址',
- 'address_en': '英文工作地址',
- 'birthday': '生日',
- 'age': '年龄',
- 'native_place': '籍贯',
- 'residence': '居住地',
- 'brand_group': '品牌组合'
- }
-
- for english_field, chinese_field in mapping_verification.items():
- value = result.get(english_field, '')
- if value:
- print(f"✓ {chinese_field} -> {english_field}: {value}")
- else:
- print(f"✗ {chinese_field} -> {english_field}: 空值")
-
- print("\n=== 测试完成 ===")
- return True
-
- except Exception as e:
- print(f"测试失败: {str(e)}")
- import traceback
- traceback.print_exc()
- return False
- if __name__ == "__main__":
- print("=" * 50)
- print("测试字段映射功能")
- print("=" * 50)
-
- # 测试字段映射
- success = test_field_mapping()
-
- print("\n" + "=" * 50)
- print("测试总结:")
- print(f"字段映射测试: {'✓ 成功' if success else '✗ 失败'}")
- print("=" * 50)
|