ocr_verify/comparator/report_generator.py

import json
import re
from typing import Dict, List
from datetime import datetime


class ReportGenerator:
    """生成比较报告"""
    
    @staticmethod
    def generate_json_report(comparison_result: Dict, output_file: str):
        """生成JSON格式报告"""
        with open(f"{output_file}.json", 'w', encoding='utf-8') as f:
            json.dump(comparison_result, f, ensure_ascii=False, indent=2)
        print(f"✅ JSON报告已生成: {output_file}.json")
    
    @staticmethod
    def generate_markdown_report(comparison_result: Dict, output_file: str):
        """生成Markdown格式报告 - 与原版本保持一致"""
        with open(f"{output_file}.md", 'w', encoding='utf-8') as f:
            f.write("# OCR结果对比报告\n\n")
            
            # 基本信息
            f.write("## 基本信息\n\n")
            f.write(f"- **文件1**: `{comparison_result['file1_path']}`\n")
            f.write(f"- **文件2**: `{comparison_result['file2_path']}`\n")
            f.write(f"- **比较时间**: {comparison_result.get('timestamp', datetime.now().strftime('%Y-%m-%d %H:%M:%S'))}\n\n")
            
            # 统计信息
            stats = comparison_result['statistics']
            f.write("## 统计信息\n\n")
            f.write(f"- 总差异数量: **{stats['total_differences']}**\n")
            f.write(f"- 表格差异: **{stats['table_differences']}**\n")
            f.write(f"- 其中表格金额差异: **{stats.get('amount_differences', 0)}**\n")
            f.write(f"- 段落差异: **{stats['paragraph_differences']}**\n")
            f.write(f"- 高严重度: **{stats.get('high_severity', 0)}**\n")
            f.write(f"- 中严重度: **{stats.get('medium_severity', 0)}**\n")
            f.write(f"- 低严重度: **{stats.get('low_severity', 0)}**\n")
            f.write(f"- 文件1表格数: {comparison_result.get('file1_tables', 0)}\n")
            f.write(f"- 文件2表格数: {comparison_result.get('file2_tables', 0)}\n")
            f.write(f"- 文件1段落数: {comparison_result.get('file1_paragraphs', 0)}\n")
            f.write(f"- 文件2段落数: {comparison_result.get('file2_paragraphs', 0)}\n\n")
            
            # 差异摘要
            if stats['total_differences'] == 0:
                f.write("## 结论\n\n")
                f.write("🎉 **完美匹配！没有发现任何差异。**\n\n")
            else:
                f.write("## 差异摘要\n\n")
                
                # ✅ 类型映射（与原版本完全一致）
                type_name_map = {
                    'table_amount': '💰 表格金额差异',
                    'table_text': '📝 表格文本差异',
                    'table_datetime': '📅 表格日期时间差异',
                    'table_pre_header': '📋 表头前内容差异',
                    'table_header_position': '📍 表头位置差异',
                    'table_header_mismatch': '⚠️ 表头不匹配',
                    'table_header_critical': '❌ 表头严重错误',
                    'table_column_type_mismatch': '🔀 列类型不匹配',
                    'table_row_missing': '🚫 表格行缺失',
                    'table_row_data': '📊 表格数据差异',
                    'table_structure': '🏗️ 表格结构差异',
                    'paragraph': '📄 段落差异',
                    'paragraph_punctuation': '🔤 段落标点差异'
                }
                
                # 按类型分组显示差异
                diff_by_type = {}
                for diff in comparison_result['differences']:
                    diff_type = diff['type']
                    if diff_type not in diff_by_type:
                        diff_by_type[diff_type] = []
                    diff_by_type[diff_type].append(diff)
                
                for diff_type, diffs in diff_by_type.items():
                    type_name = type_name_map.get(diff_type, f'❓ {diff_type}')
                    
                    f.write(f"### {type_name} ({len(diffs)}个)\n\n")
                    
                    for i, diff in enumerate(diffs, 1):
                        f.write(f"**{i}. {diff.get('position', 'N/A')}**\n")
                        f.write(f"- 文件1: `{diff.get('file1_value', '')}`\n")
                        f.write(f"- 文件2: `{diff.get('file2_value', '')}`\n")
                        f.write(f"- 说明: {diff.get('description', 'N/A')}\n")
                        if 'severity' in diff:
                            severity_icon = {'critical': '🔴', 'high': '🟠', 'medium': '🟡', 'low': '🟢'}
                            f.write(f"- 严重度: {severity_icon.get(diff['severity'], '⚪')} {diff['severity']}\n")
                        f.write("\n")
            
            # 详细差异列表
            if comparison_result['differences']:
                f.write("## 详细差异列表\n\n")
                f.write("| 序号 | 类型 | 位置 | 文件1内容 | 文件2内容 | 描述 | 严重度 |\n")
                f.write("| --- | --- | --- | --- | --- | --- | --- |\n")
                
                for i, diff in enumerate(comparison_result['differences'], 1):
                    severity = diff.get('severity', 'N/A')
                    position = diff.get('position', 'N/A')
                    file1_value = str(diff.get('file1_value', ''))[:50]
                    file2_value = str(diff.get('file2_value', ''))[:50]
                    description = diff.get('description', 'N/A')
                    
                    # 截断长文本
                    if len(str(diff.get('file1_value', ''))) > 50:
                        file1_value += '...'
                    if len(str(diff.get('file2_value', ''))) > 50:
                        file2_value += '...'
                    
                    f.write(f"| {i} | {diff['type']} | {position} | ")
                    f.write(f"`{file1_value}` | ")
                    f.write(f"`{file2_value}` | ")
                    f.write(f"{description} | {severity} |\n")
        
        print(f"✅ Markdown报告已生成: {output_file}.md")
    
    @staticmethod
    def generate_report(comparison_result: Dict, output_file: str, output_format: str):
        """根据格式生成报告"""
        if output_format in ['json', 'both']:
            ReportGenerator.generate_json_report(comparison_result, output_file)
        
        if output_format in ['markdown', 'both']:
            ReportGenerator.generate_markdown_report(comparison_result, output_file)