"""
显示批量测试结果摘要
"""
import json

# 读取测试结果
with open('test_reports_full/test_report.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

summary = data['summary']
results = data['results']

print("=" * 80)
print("批量测试结果摘要")
print("=" * 80)

print(f"\n总体统计:")
print(f"  处理PDF数量: {summary['total_processed']}")
print(f"  平均处理时间: {summary['avg_processing_time']:.1f}秒")

print(f"\nCMA提取结果:")
print(f"  精确匹配: {summary['cma']['exact']}")
print(f"  部分匹配: {summary['cma']['partial']}")
print(f"  可接受: {summary['cma']['acceptable']}")
print(f"  未匹配: {summary['cma']['no_match']}")
print(f"  准确率: {summary['cma']['accuracy']*100:.1f}%")

print(f"\n机构提取结果:")
print(f"  精确匹配: {summary['institution']['exact']}")
print(f"  部分匹配: {summary['institution']['partial']}")
print(f"  可接受: {summary['institution']['acceptable']}")
print(f"  未匹配: {summary['institution']['no_match']}")
print(f"  准确率: {summary['institution']['accuracy']*100:.1f}%")

print(f"\n详细结果 (前10个):")
print("-" * 80)
for i, r in enumerate(results[:10], 1):
    pdf_name = r['pdf_name'][:40]
    cma = r['extracted'].get('cma', 'N/A')
    expected_cma = r['expected'].get('cma', 'N/A')
    inst = r['extracted'].get('institution', 'N/A')[:30]
    cma_match = r['comparison']['cma'].get('match_type', 'unknown')

    print(f"{i}. {pdf_name}")
    print(f"   CMA: {cma} (期望: {expected_cma}) [{cma_match}]")
    print(f"   机构: {inst}...")

# 显示失败的PDF
print(f"\n失败的PDF:")
print("-" * 80)
failed = [r for r in results if r['comparison']['cma'].get('match_type') == 'no_match']
if failed:
    for r in failed:
        pdf_name = r['pdf_name'][:40]
        expected_cma = r['expected'].get('cma', 'N/A')
        extracted_cma = r['extracted'].get('cma', 'N/A')
        print(f"- {pdf_name}")
        print(f"  期望: {expected_cma}, 提取: {extracted_cma}")
else:
    print("无")

print("\n" + "=" * 80)
print("提示: 在浏览器中打开 test_reports_full/summary.html 查看详细的可视化报告")
print("=" * 80)