"""
从模板文件重新提取所有检测项目的临床意义
生成正确的 template_explanations.json
"""
from docx import Document
import json

def main():
    doc = Document('template_complete.docx')
    
    explanations = {}
    
    # 遍历所有表格
    for table in doc.tables:
        rows = list(table.rows)
        
        for i, row in enumerate(rows):
            cells = row.cells
            if not cells:
                continue
            
            first_cell = cells[0].text.strip()
            
            # 跳过空行、表头、模块标题
            if not first_cell:
                continue
            if 'Abb' in first_cell or '简称' in first_cell:
                continue
            if 'Clinical' in first_cell:
                continue
            
            # 检查是否是ABB行（短文本，不含占位符，不含中文模块名）
            if len(first_cell) > 40 or '{{' in first_cell:
                continue
            
            # 跳过模块标题（包含换行符和中文）
            if '\n' in first_cell and any('\u4e00' <= c <= '\u9fff' for c in first_cell):
                continue
            
            # 这是一个ABB，查找下一行的临床意义
            abb = first_cell
            
            # 在当前行或下一行查找临床意义
            clinical_text = None
            
            # 先检查当前行的其他单元格
            for cell in cells:
                text = cell.text.strip()
                if 'Clinical Significance:' in text and '临床意义：' in text:
                    clinical_text = text
                    break
            
            # 如果当前行没有，检查下一行
            if not clinical_text and i + 1 < len(rows):
                next_row = rows[i + 1]
                for cell in next_row.cells:
                    text = cell.text.strip()
                    if 'Clinical Significance:' in text and '临床意义：' in text:
                        clinical_text = text
                        break
            
            if clinical_text:
                # 提取英文和中文
                parts = clinical_text.split('临床意义：')
                if len(parts) == 2:
                    en = parts[0].replace('Clinical Significance:', '').strip()
                    cn = parts[1].strip()
                    
                    if en and cn:
                        # 标准化ABB名称
                        abb_key = abb.upper().strip()
                        abb_key = abb_key.replace(' - ', '-').replace('（', '(').replace('）', ')')
                        
                        if abb_key not in explanations:
                            explanations[abb_key] = {
                                'clinical_en': en,
                                'clinical_cn': cn
                            }
    
    print(f'从模板提取了 {len(explanations)} 个项目的临床意义')
    
    # 保存
    with open('template_explanations.json', 'w', encoding='utf-8') as f:
        json.dump(explanations, f, ensure_ascii=False, indent=2)
    
    print(f'已保存到 template_explanations.json')
    
    # 验证 Color
    if 'COLOR' in explanations:
        print(f'\nCOLOR 验证:')
        print(f'EN: {explanations["COLOR"]["clinical_en"][:80]}...')
        print(f'CN: {explanations["COLOR"]["clinical_cn"][:80]}...')

if __name__ == '__main__':
    main()