#!/usr/bin/env python3
"""生成验证报告"""

import json
from pathlib import Path

results_dir = Path("./evaluation/auto_results")

# 读取两篇文献的结果
papers = [
    "短柄AP2s12864-016-2968-8_phylogeny_v2.json",
    "番茄p450基因家族BMCgenomics2020_phylogeny_v2.json"
]

print("=" * 80)
print("基因家族系统发育提取验证报告")
print("=" * 80)
print()

for paper_file in papers:
    path = results_dir / paper_file
    if not path.exists():
        print(f"❌ 未找到: {paper_file}")
        continue
    
    with open(path, 'r') as f:
        data = json.load(f)
    
    print(f"📄 {data.get('pdf_name', paper_file)}")
    print("-" * 80)
    print(f"   基因家族: {data.get('gene_family', 'N/A')}")
    print(f"   物种: {data.get('species', 'N/A')}")
    print(f"   总基因数: {data.get('total_genes', 0)}")
    print(f"   总组数: {data.get('total_groups', 0)}")
    print(f"   分类类型: {data.get('classification_type', 'N/A')}")
    print(f"   置信度: {data.get('confidence', 'low')}")
    print()
    
    if data.get('groups'):
        print("   分组详情:")
        for group_name, genes in sorted(data['groups'].items()):
            print(f"      • {group_name}: {len(genes)} 个基因")
    else:
        print("   ⚠️ 未提取到分组信息")
    
    if data.get('notes'):
        print()
        print("   备注:")
        for note in data['notes']:
            print(f"      ℹ {note}")
    
    print()
    print()

print("=" * 80)
print("分析总结")
print("=" * 80)
print()