"""
验证字段编码修复结果，并处理剩余的真正问题
"""
import os
import pymysql
import re
from typing import Dict, List

# 数据库连接配置
DB_CONFIG = {
    'host': os.getenv('DB_HOST', '152.136.177.240'),
    'port': int(os.getenv('DB_PORT', 5012)),
    'user': os.getenv('DB_USER', 'finyx'),
    'password': os.getenv('DB_PASSWORD', '6QsGK6MpePZDE57Z'),
    'database': os.getenv('DB_NAME', 'finyx'),
    'charset': 'utf8mb4'
}

TENANT_ID = 615873064429507639

def is_chinese(text: str) -> bool:
    """判断字符串是否包含中文字符"""
    if not text:
        return False
    return bool(re.search(r'[\u4e00-\u9fff]', text))


def verify_fix():
    """验证修复结果"""
    conn = pymysql.connect(**DB_CONFIG)
    cursor = conn.cursor(pymysql.cursors.DictCursor)
    
    print("="*80)
    print("验证字段编码修复结果")
    print("="*80)
    
    # 查询所有字段
    cursor.execute("""
        SELECT id, name, filed_code, field_type, state
        FROM f_polic_field
        WHERE tenant_id = %s
        ORDER BY name
    """, (TENANT_ID,))
    
    fields = cursor.fetchall()
    
    # 找出仍然包含中文的field_code
    chinese_fields = []
    for field in fields:
        if field['filed_code'] and is_chinese(field['filed_code']):
            chinese_fields.append(field)
    
    print(f"\n总共 {len(fields)} 个字段")
    print(f"仍有 {len(chinese_fields)} 个字段的field_code包含中文:\n")
    
    if chinese_fields:
        for field in chinese_fields:
            print(f"  ID: {field['id']}")
            print(f"  名称: {field['name']}")
            print(f"  field_code: {field['filed_code']}")
            print(f"  field_type: {field['field_type']}")
            print()
    
    # 检查重复的字段名称
    name_to_fields = {}
    for field in fields:
        name = field['name']
        if name not in name_to_fields:
            name_to_fields[name] = []
        name_to_fields[name].append(field)
    
    duplicates = {name: fields_list for name, fields_list in name_to_fields.items() 
                 if len(fields_list) > 1}
    
    print(f"\n仍有 {len(duplicates)} 个重复的字段名称:\n")
    for name, fields_list in duplicates.items():
        print(f"  字段名称: {name} (共 {len(fields_list)} 条记录)")
        for field in fields_list:
            print(f"    - ID: {field['id']}, field_code: {field['filed_code']}, "
                  f"field_type: {field['field_type']}, state: {field['state']}")
        print()
    
    # 检查f_polic_file_field表中的关联关系
    print("="*80)
    print("检查 f_polic_file_field 表")
    print("="*80)
    
    cursor.execute("""
        SELECT fff.id, fff.file_id, fff.filed_id, 
               fc.name as file_name, f.name as field_name, f.filed_code
        FROM f_polic_file_field fff
        LEFT JOIN f_polic_file_config fc ON fff.file_id = fc.id
        LEFT JOIN f_polic_field f ON fff.filed_id = f.id
        WHERE fff.tenant_id = %s AND f.filed_code IS NOT NULL
        ORDER BY fff.file_id, fff.filed_id
    """, (TENANT_ID,))
    
    relations = cursor.fetchall()
    
    # 检查是否有重复的关联关系
    relation_keys = {}
    for rel in relations:
        key = (rel['file_id'], rel['filed_id'])
        if key not in relation_keys:
            relation_keys[key] = []
        relation_keys[key].append(rel)
    
    duplicate_relations = {key: records for key, records in relation_keys.items() 
                          if len(records) > 1}
    
    print(f"\n总共 {len(relations)} 个关联关系")
    print(f"发现 {len(duplicate_relations)} 个重复的关联关系")
    
    # 检查使用中文field_code的关联关系
    chinese_relations = [rel for rel in relations 
                         if rel['filed_code'] and is_chinese(rel['filed_code'])]
    
    print(f"使用中文field_code的关联关系: {len(chinese_relations)} 个")
    
    if chinese_relations:
        print("\n前10个使用中文field_code的关联关系:")
        for rel in chinese_relations[:10]:
            print(f"  - 文件: {rel['file_name']}, 字段: {rel['field_name']}, "
                  f"field_code: {rel['filed_code']}")
    
    cursor.close()
    conn.close()
    
    return {
        'total_fields': len(fields),
        'chinese_fields': len(chinese_fields),
        'duplicate_names': len(duplicates),
        'duplicate_relations': len(duplicate_relations),
        'chinese_relations': len(chinese_relations)
    }


if __name__ == '__main__':
    result = verify_fix()
    print("\n" + "="*80)
    print("验证完成")
    print("="*80)
    print(f"总字段数: {result['total_fields']}")
    print(f"中文field_code字段数: {result['chinese_fields']}")
    print(f"重复字段名称数: {result['duplicate_names']}")
    print(f"重复关联关系数: {result['duplicate_relations']}")
    print(f"使用中文field_code的关联关系数: {result['chinese_relations']}")