import difflib import json from typing import List, Dict from compare_ocr_results import OCRResultComparator class OCRResultComparatorUnifiedDiff(OCRResultComparator): # 继承自OCRResultComparator以复用部分功能 def __init__(self): super().__init__() def generate_unified_diff(self, paras1: List[str], paras2: List[str], file1_path: str, file2_path: str) -> Dict: """ 生成类似git diff的统一差异格式，并返回结构化数据 """ # 直接调用进行预处理 file1_lines = paras1 file2_lines = paras2 # 使用unified_diff生成差异 diff = difflib.unified_diff( file1_lines, file2_lines, fromfile=file1_path, tofile=file2_path, lineterm='' # 确保每行末尾不添加额外字符 ) # 将差异生成器转换为列表 diff_output = list(diff) # 解析diff输出并生成结构化数据 structured_diff = self._parse_unified_diff(diff_output, file1_lines, file2_lines, file1_path, file2_path) return structured_diff def _parse_unified_diff(self, diff_lines: List[str], file1_lines: List[str], file2_lines: List[str], file1_path: str, file2_path: str) -> Dict: """解析unified diff输出并生成结构化数据""" differences = [] current_hunk = None file1_line_num = 0 file2_line_num = 0 for line in diff_lines: if line.startswith('---') or line.startswith('+++'): continue elif line.startswith('@@'): # 解析hunk头部，例如: @@ -1,5 +1,4 @@ import re match = re.match(r'@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@', line) if match: file1_start = int(match.group(1)) file1_count = int(match.group(2)) if match.group(2) else 1 file2_start = int(match.group(3)) file2_count = int(match.group(4)) if match.group(4) else 1 current_hunk = { 'file1_start': file1_start, 'file1_count': file1_count, 'file2_start': file2_start, 'file2_count': file2_count } file1_line_num = file1_start - 1 # 转为0基索引 file2_line_num = file2_start - 1 elif line.startswith(' '): # 未改变的行 file1_line_num += 1 file2_line_num += 1 elif line.startswith('-'): # 文件1中删除的行 content = line[1:] # 去掉'-'前缀 differences.append({ 'type': 'paragraph', 'position': f'段落{file1_line_num + 1}', 'file1_value': content, 'file2_value': "", 'description': '文件1中独有的段落', 'similarity': 0.0, 'severity': 'medium', 'line_number': file1_line_num + 1, 'change_type': 'deletion' }) file1_line_num += 1 elif line.startswith('+'): # 文件2中添加的行 content = line[1:] # 去掉'+'前缀 differences.append({ 'type': 'paragraph', 'position': f'段落{file2_line_num + 1}', 'file1_value': "", 'file2_value': content, 'description': '文件2中独有的段落', 'similarity': 0.0, 'severity': 'medium', 'line_number': file2_line_num + 1, 'change_type': 'addition' }) file2_line_num += 1 # 计算统计信息 stats = { 'total_differences': len(differences), 'table_differences': 0, # diff不包含表格差异 'paragraph_differences': len(differences), 'amount_differences': 0, 'high_severity': len([d for d in differences if d.get('severity') == 'high']), 'medium_severity': len([d for d in differences if d.get('severity') == 'medium']), 'low_severity': len([d for d in differences if d.get('severity') == 'low']), 'deletions': len([d for d in differences if d.get('change_type') == 'deletion']), 'additions': len([d for d in differences if d.get('change_type') == 'addition']) } return { 'differences': differences, 'statistics': stats, 'file1_tables': 0, 'file2_tables': 0, 'file1_paragraphs': len(file1_lines), 'file2_paragraphs': len(file2_lines), 'file1_path': file1_path, 'file2_path': file2_path, 'diff_type': 'unified_diff' } def generate_unified_diff_report(self, paras1: List[str], paras2: List[str], file1_path: str, file2_path: str, output_file: str): """生成unified diff的JSON和Markdown报告""" # 生成结构化diff数据 diff_data = self.generate_unified_diff(paras1, paras2, file1_path, file2_path) # 添加时间戳 import datetime diff_data['timestamp'] = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') # 生成JSON报告 json_file = f"{output_file}_unified_diff.json" with open(json_file, 'w', encoding='utf-8') as f: json.dump(diff_data, f, ensure_ascii=False, indent=2) # 生成Markdown报告 md_file = f"{output_file}_unified_diff.md" self._generate_unified_diff_markdown(diff_data, md_file) print(f"📄 Unified Diff JSON报告: {json_file}") print(f"📝 Unified Diff Markdown报告: {md_file}") return diff_data def _generate_unified_diff_markdown(self, diff_data: Dict, output_file: str): """生成unified diff的Markdown报告""" with open(output_file, 'w', encoding='utf-8') as f: f.write("# OCR结果Unified Diff对比报告\n\n") # 基本信息 f.write("## 基本信息\n\n") f.write(f"- **文件1**: `{diff_data['file1_path']}`\n") f.write(f"- **文件2**: `{diff_data['file2_path']}`\n") f.write(f"- **比较时间**: {diff_data.get('timestamp', 'N/A')}\n") f.write(f"- **对比方式**: Unified Diff\n\n") # 统计信息 stats = diff_data['statistics'] f.write("## 统计信息\n\n") f.write(f"- 总差异数量: **{stats['total_differences']}**\n") f.write(f"- 删除行数: **{stats['deletions']}**\n") f.write(f"- 添加行数: **{stats['additions']}**\n") f.write(f"- 文件1段落数: {diff_data['file1_paragraphs']}\n") f.write(f"- 文件2段落数: {diff_data['file2_paragraphs']}\n\n") # 差异详情 if diff_data['differences']: f.write("## 差异详情\n\n") # 按变更类型分组 deletions = [d for d in diff_data['differences'] if d['change_type'] == 'deletion'] additions = [d for d in diff_data['differences'] if d['change_type'] == 'addition'] if deletions: f.write(f"### 🗑️ 删除内容 ({len(deletions)}项)\n\n") for i, diff in enumerate(deletions, 1): f.write(f"**{i}. 第{diff['line_number']}行**\n") f.write(f"```\n{diff['file1_value']}\n```\n\n") if additions: f.write(f"### ➕ 新增内容 ({len(additions)}项)\n\n") for i, diff in enumerate(additions, 1): f.write(f"**{i}. 第{diff['line_number']}行**\n") f.write(f"```\n{diff['file2_value']}\n```\n\n") # 详细差异表格 f.write("## 详细差异列表\n\n") f.write("| 序号 | 类型 | 行号 | 变更类型 | 内容 | 描述 |\n") f.write("| --- | --- | --- | --- | --- | --- |\n") for i, diff in enumerate(diff_data['differences'], 1): change_icon = "🗑️" if diff['change_type'] == 'deletion' else "➕" content = diff['file1_value'] if diff['change_type'] == 'deletion' else diff['file2_value'] f.write(f"| {i} | {change_icon} | {diff['line_number']} | {diff['change_type']} | ") f.write(f"`{content[:50]}{'...' if len(content) > 50 else ''}` | ") f.write(f"{diff['description']} |\n") else: f.write("## 结论\n\n") f.write("🎉 **完美匹配！没有发现任何差异。**\n\n")