"""
检查template_finish文件夹下的模板文件占位符是否可以被正确识别
"""
import os
import re
from pathlib import Path
from docx import Document
from collections import defaultdict


def extract_placeholders_from_docx(file_path):
    """
    从docx文件中提取所有占位符
    
    Args:
        file_path: docx文件路径
        
    Returns:
        占位符列表，格式: ['field_code1', 'field_code2', ...]
    """
    placeholders = set()
    pattern = r'\{\{([^}]+)\}\}'  # 匹配 {{field_code}} 格式
    
    try:
        doc = Document(file_path)
        
        # 从段落中提取占位符
        for paragraph in doc.paragraphs:
            text = paragraph.text
            matches = re.findall(pattern, text)
            for match in matches:
                placeholders.add(match.strip())
        
        # 从表格中提取占位符
        for table in doc.tables:
            for row in table.rows:
                for cell in row.cells:
                    for paragraph in cell.paragraphs:
                        text = paragraph.text
                        matches = re.findall(pattern, text)
                        for match in matches:
                            placeholders.add(match.strip())
        
    except Exception as e:
        print(f"  错误: 读取文件失败 - {str(e)}")
        return []
    
    return sorted(list(placeholders))


def check_templates_in_directory(base_dir):
    """
    检查目录下所有模板文件的占位符
    
    Args:
        base_dir: 模板文件根目录
    """
    base_path = Path(base_dir)
    if not base_path.exists():
        print(f"错误: 目录不存在 - {base_dir}")
        return
    
    # 统计信息
    total_files = 0
    valid_files = 0
    invalid_files = 0
    all_placeholders = defaultdict(set)  # 文件路径 -> 占位符集合
    all_unique_placeholders = set()  # 所有唯一的占位符
    
    print("=" * 80)
    print("模板文件占位符检查报告")
    print("=" * 80)
    print()
    
    # 遍历所有docx文件
    for docx_file in base_path.rglob("*.docx"):
        # 跳过临时文件（以~$开头的文件）
        if docx_file.name.startswith("~$"):
            continue
        
        total_files += 1
        relative_path = docx_file.relative_to(base_path)
        
        print(f"[{total_files}] 检查文件: {relative_path}")
        
        # 提取占位符
        placeholders = extract_placeholders_from_docx(str(docx_file))
        
        if placeholders:
            valid_files += 1
            all_placeholders[str(relative_path)] = placeholders
            all_unique_placeholders.update(placeholders)
            
            print(f"  ✓ 找到 {len(placeholders)} 个占位符:")
            for i, placeholder in enumerate(placeholders, 1):
                print(f"    {i}. {{{{ {placeholder} }}}}")
        else:
            invalid_files += 1
            print(f"  ⚠ 未找到占位符")
        
        print()
    
    # 打印汇总信息
    print("=" * 80)
    print("检查汇总")
    print("=" * 80)
    print(f"总文件数: {total_files}")
    print(f"包含占位符的文件: {valid_files}")
    print(f"未找到占位符的文件: {invalid_files}")
    print(f"唯一占位符总数: {len(all_unique_placeholders)}")
    print()
    
    # 打印所有唯一占位符
    if all_unique_placeholders:
        print("所有唯一占位符列表:")
        for i, placeholder in enumerate(sorted(all_unique_placeholders), 1):
            print(f"  {i}. {{{{ {placeholder} }}}}")
        print()
    
    # 打印每个文件的占位符详情
    print("=" * 80)
    print("各文件占位符详情")
    print("=" * 80)
    for file_path, placeholders in sorted(all_placeholders.items()):
        print(f"\n文件: {file_path}")
        print(f"占位符数量: {len(placeholders)}")
        for placeholder in placeholders:
            print(f"  - {{{{ {placeholder} }}}}")
    
    # 返回结果供其他脚本使用
    return {
        'total_files': total_files,
        'valid_files': valid_files,
        'invalid_files': invalid_files,
        'all_placeholders': dict(all_placeholders),
        'unique_placeholders': sorted(all_unique_placeholders)
    }


def main():
    """主函数"""
    template_dir = os.path.join(os.path.dirname(__file__), 'template_finish')
    
    print(f"检查目录: {template_dir}")
    print()
    
    result = check_templates_in_directory(template_dir)
    
    if result:
        print("\n" + "=" * 80)
        print("检查完成！")
        print("=" * 80)


if __name__ == '__main__':
    main()