fix:生成的内容

cloudroam

昨天 90e496298b21f0594b85535ec47d26d2d7d5a9ed

 app.py

@@ -203,13 +203,14 @@
        # 还款短信特征
        repayment_keywords = [
            "还款", "账单", "信用卡", "借款", "贷款", "逾期", "欠款", "最低还款",
            "应还金额", "到期还款", "还清", "应还", "还款日", "账单￥", "账单¥", "查账还款"
            "应还金额", "到期还款", "还清", "应还", "还款日", "账单￥", "账单¥", "查账还款",
            "扣款用于", "房贷还款", "信用卡还款", "车贷还款", "应还款额", "最低还款额"
        ]
        
        # 收入短信特征
        income_keywords = [
            "收入", "转账", "入账", "到账", "支付", "工资", "报销", "余额", 
            "成功收款", "收到", "款项"
            "成功收款", "收到", "款项", "收入金额"
        ]
        
        # 航班/火车票特征
@@ -342,8 +343,15 @@
            # 快递关键词
            "快递", "包裹", "取件码", "取件", "签收", "派送", "配送",
            # 收入关键词
            "收入", "转账", "入账", "到账", "支付成功", "工资"
            "收入", "转账", "入账", "到账", "支付成功", "工资", "支付宝转账", "微信转账"
        ]
        
        # 先检查是否为收入短信（优先于通知判断）
        income_indicators = ["收入", "入账", "转账", "工资"]
        for indicator in income_indicators:
            if indicator in text and "元" in text:
                # 可能是收入短信，不要判断为通知
                return False
        
        # 运营商余额通知特征
        telecom_balance_patterns = [
@@ -458,20 +466,62 @@
                    if word in code:
                        code = code[:code.index(word)]
                
                # 只保留字母、数字和连字符
                code = ''.join(c for c in code if c.isalnum() or c == "-")
                # 针对不同快递公司采取不同策略
                if "丰巢" in text or "蜂巢" in text:
                    # 对于丰巢快递，只保留数字
                    code = ''.join(c for c in code if c.isdigit())
                elif "中国邮政" in text:
                    # 对于中国邮政，尝试提取完整货位号
                    cargo_match = re.search(r'货号[:：]\s*([0-9A-Za-z\-]+)', text)
                    if cargo_match:
                        code = cargo_match.group(1)
                    else:
                        # 保留原始格式（字母、数字和连字符）
                        code = ''.join(c for c in code if c.isalnum() or c == "-")
                else:
                    # 对于其他快递，保留字母、数字和连字符
                    code = ''.join(c for c in code if c.isalnum() or c == "-")
                
                # 确保格式正确
                parts = code.split("-")
                valid_parts = []
                for part in parts:
                    if part and any(c.isalnum() for c in part):
                        valid_parts.append(part)
                
                if valid_parts:
                    result["pickup_code"] = "-".join(valid_parts)
                if "丰巢" in text or "蜂巢" in text:
                    # 对于丰巢快递，只保留数字
                    if code.isdigit():
                        result["pickup_code"] = code
                    else:
                        # 如果没有数字，尝试再次从文本中匹配纯数字取件码
                        pickup_code_match = re.search(r'码[^0-9]*(\d+)', text)
                        if pickup_code_match:
                            result["pickup_code"] = pickup_code_match.group(1)
                        else:
                            result["pickup_code"] = None
                elif "中国邮政" in text:
                    # 对于中国邮政，验证格式是否合理
                    if re.match(r'[0-9A-Za-z\-]+', code):
                        result["pickup_code"] = code
                    else:
                        # 二次尝试：从文本中直接获取货位号
                        cargo_match = re.search(r'货号[:：]\s*([0-9A-Za-z\-]+)', text)
                        if cargo_match:
                            result["pickup_code"] = cargo_match.group(1)
                        else:
                            # 最后尝试：提取"取件密码"后的纯数字序列
                            password_match = re.search(r'密码\s*(\d+)', text)
                            if password_match:
                                result["pickup_code"] = password_match.group(1)
                            else:
                                result["pickup_code"] = None
                else:
                    result["pickup_code"] = None
                    # 对于其他快递，保持原有逻辑
                    parts = code.split("-")
                    valid_parts = []
                    for part in parts:
                        if part and any(c.isalnum() for c in part):
                            valid_parts.append(part)
                    
                    if valid_parts:
                        result["pickup_code"] = "-".join(valid_parts)
                    else:
                        result["pickup_code"] = None

            # 清理公司名称
            if result["company"]:
@@ -480,7 +530,16 @@
                for word in invalid_words:
                    if company.endswith(word):
                        company = company[:-len(word)]
                
                # 特殊处理中国邮政
                if company == "中国" and "中国邮政" in text:
                    company = "邮政"
                elif "中国邮政" in text and not company:
                    company = "邮政"
                
                result["company"] = company.strip()
            elif "中国邮政" in text:  # 如果NER未识别但文本中有中国邮政
                result["company"] = "邮政"

            # 清理地址
            if result["address"]:
@@ -623,7 +682,8 @@
                
                # 尝试查找最低还款金额
                min_amount_match = re.search(r'最低还款([\d,]+\.?\d*)(?:元|块钱|块|万元|万)?', context)
                if min_amount_match and "MIN_CODE" in current_entity["type"]:
                # 修复：确保current_entity存在且有type属性再使用
                if min_amount_match and 'current_entity' in locals() and current_entity is not None and "MIN_CODE" in current_entity["type"]:
                    return min_amount_match.group(1)  # 直接返回匹配到的最低还款金额，保留原始格式
                    
                # 在上下文中查找完整金额
@@ -1360,6 +1420,103 @@
        # 保存原始短信内容到文件
        save_sms_to_file(text)
            
        # 已还清或已结清的短信模式
        already_paid_patterns = [
            r"已还清",
            r"已结清",
            r"还款.*?入账后.*?已还清",
            r"还款.*?入账.*?结清"
        ]
        
        # 检查是否为已还清/已结清的短信
        for pattern in already_paid_patterns:
            if re.search(pattern, text):
                logger.info(f"识别为已还清/已结清短信，归类为其他: {text[:30]}...")
                category = "其他"
                save_sms_to_file(text, category, 1.0)
                return jsonify({
                    "status": "success",
                    "data": {
                        "category": category,
                        "details": {}
                    }
                })
            
        # 银行收入短信特征识别
        income_patterns = [
            r"收入金额[\d,.]+元",
            r"账户.*?收入.*?[\d,.]+元",
            r"账户.*?工资",
            r"工资.*?收入",
            r"入账[\d,.]+元",
            # 添加新模式匹配南京银行等类似格式
            r"收入\d+\.\d+元",
            r"账号.*?收入\d+\.\d+元",
            r"尾号\d+的账号.*?收入\d+\.\d+元",
            r"支付宝转账",
            r"转账.*?收入"
        ]
        
        # 银行还款短信特征识别
        repayment_patterns = [
            r"信用卡.*?还款",
            r"账单.*?[\d,.]+元",
            r"应还款额.*?[\d,.]+元",
            r"最低还款额.*?[\d,.]+元",
            r"到期还款日",
            r"扣款.*?用于.*?还款",
            r"扣款.*?用于.*?贷款",
            r"扣款.*?用于.*?信用卡",
            r"车贷还款",
            r"房贷还款",
            r"贷款还款",
            r"信用卡账单",
            r"下次还款日"
        ]
        
        # 检查是否为收入短信
        for pattern in income_patterns:
            if re.search(pattern, text):
                logger.info(f"识别为收入短信: {text[:30]}...")
                category = "收入"
                details = model_manager.extract_income_entities(text)
                save_sms_to_file(text, category, 1.0)
                return jsonify({
                    "status": "success",
                    "data": {
                        "category": category,
                        "details": details
                    }
                })
        
        # 检查是否为还款短信
        for pattern in repayment_patterns:
            if re.search(pattern, text):
                # 二次检查：如果包含"已还清"或"已结清"等词，归类为"其他"
                if any(re.search(paid_pattern, text) for paid_pattern in already_paid_patterns):
                    logger.info(f"虽然识别为还款短信，但包含已还清/已结清，归类为其他: {text[:30]}...")
                    category = "其他"
                    save_sms_to_file(text, category, 1.0)
                    return jsonify({
                        "status": "success",
                        "data": {
                            "category": category,
                            "details": {}
                        }
                    })
                
                logger.info(f"识别为还款短信: {text[:30]}...")
                category = "还款"
                details = model_manager.extract_repayment_entities(text)
                save_sms_to_file(text, category, 1.0)
                return jsonify({
                    "status": "success",
                    "data": {
                        "category": category,
                        "details": details
                    }
                })
        
        # 特定短信识别逻辑 - 针对百度通知和招商银行账单
        # 识别百度通知
        if "百度智能云" in text and "尊敬的用户" in text and "免费额度" in text:
@@ -1376,6 +1533,19 @@
        
        # 识别招商银行账单
        if "招商银行" in text and ("账单￥" in text or "账单¥" in text or "还款日" in text):
            # 检查是否为已还清/已结清短信
            if any(re.search(paid_pattern, text) for paid_pattern in already_paid_patterns):
                logger.info(f"招商银行短信包含已还清/已结清，归类为其他: {text[:30]}...")
                category = "其他"
                save_sms_to_file(text, category, 1.0)
                return jsonify({
                    "status": "success",
                    "data": {
                        "category": category,
                        "details": {}
                    }
                })
                
            logger.info(f"直接识别为招商银行还款短信: {text[:30]}...")
            category = "还款"
            details = model_manager.extract_repayment_entities(text)