first commit

old/app/models/__init__.py

@@ -0,0 +1,46 @@
+from sqlalchemy import create_engine
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import sessionmaker, scoped_session
+import os
+import sys
+
+# 修改相对导入为绝对导入
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+from config import active_config
+
+# 创建数据库引擎
+engine = create_engine(active_config.SQLALCHEMY_DATABASE_URI)
+
+# 创建会话工厂
+session_factory = sessionmaker(bind=engine)
+Session = scoped_session(session_factory)
+
+# 创建模型基类
+Base = declarative_base()
+
+# 获取数据库会话
+def get_session():
+    """获取数据库会话"""
+    return Session()
+
+# 初始化数据库
+def init_db():
+    """初始化数据库，创建所有表"""
+    # 导入所有模型以确保它们被注册
+    from .domain import Domain
+    from .mailbox import Mailbox
+    from .email import Email
+    from .attachment import Attachment
+    
+    # 创建表
+    Base.metadata.create_all(engine)
+    
+    return get_session()
+
+# 导出模型类
+from .domain import Domain
+from .mailbox import Mailbox
+from .email import Email
+from .attachment import Attachment
+
+__all__ = ['Base', 'get_session', 'init_db', 'Domain', 'Mailbox', 'Email', 'Attachment']

old/app/models/attachment.py

@@ -0,0 +1,71 @@
+from sqlalchemy import Column, Integer, String, DateTime, ForeignKey, LargeBinary
+from sqlalchemy.orm import relationship
+from datetime import datetime
+import os
+
+from . import Base
+
+class Attachment(Base):
+    """附件模型"""
+    __tablename__ = 'attachments'
+
+    id = Column(Integer, primary_key=True)
+    email_id = Column(Integer, ForeignKey('emails.id'), nullable=False, index=True)
+    filename = Column(String(255), nullable=False)
+    content_type = Column(String(100), nullable=True)
+    size = Column(Integer, nullable=False, default=0)
+    storage_path = Column(String(500), nullable=True)  # 用于文件系统存储
+    content = Column(LargeBinary, nullable=True)  # 用于小型附件的直接存储
+    created_at = Column(DateTime, default=datetime.utcnow)
+    
+    # 关联关系
+    email = relationship("Email", back_populates="attachments")
+    
+    @property
+    def is_stored_in_fs(self):
+        """判断附件是否存储在文件系统中"""
+        return bool(self.storage_path and not self.content)
+    
+    def save_to_filesystem(self, content, base_path):
+        """将附件保存到文件系统"""
+        # 确保目录存在
+        os.makedirs(base_path, exist_ok=True)
+        
+        # 创建文件路径
+        file_path = os.path.join(
+            base_path, 
+            f"{self.email_id}_{self.id}_{self.filename}"
+        )
+        
+        # 写入文件
+        with open(file_path, 'wb') as f:
+            f.write(content)
+        
+        # 更新对象属性
+        self.storage_path = file_path
+        self.size = len(content)
+        self.content = None  # 清空内存中的内容
+        
+        return file_path
+    
+    def get_content(self, attachments_dir=None):
+        """获取附件内容，无论是从数据库还是文件系统"""
+        if self.content:
+            return self.content
+            
+        if self.storage_path and os.path.exists(self.storage_path):
+            with open(self.storage_path, 'rb') as f:
+                return f.read()
+                
+        return None
+        
+    def to_dict(self):
+        """转换为字典，用于API响应"""
+        return {
+            "id": self.id,
+            "email_id": self.email_id,
+            "filename": self.filename,
+            "content_type": self.content_type,
+            "size": self.size,
+            "created_at": self.created_at.isoformat() if self.created_at else None
+        } 

old/app/models/domain.py

@@ -0,0 +1,35 @@
+from sqlalchemy import Column, Integer, String, Boolean, DateTime
+from sqlalchemy.orm import relationship
+from datetime import datetime
+
+from . import Base
+
+
+class Domain(Base):
+    """邮件域名模型"""
+    __tablename__ = 'domains'
+    
+    id = Column(Integer, primary_key=True)
+    name = Column(String(255), unique=True, nullable=False, index=True)
+    description = Column(String(500), nullable=True)
+    active = Column(Boolean, default=True)
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    
+    # 关系
+    mailboxes = relationship("Mailbox", back_populates="domain", cascade="all, delete-orphan")
+    
+    def __repr__(self):
+        return f"<Domain {self.name}>"
+        
+    def to_dict(self):
+        """转换为字典，用于API响应"""
+        return {
+            "id": self.id,
+            "name": self.name,
+            "description": self.description,
+            "active": self.active,
+            "created_at": self.created_at.isoformat() if self.created_at else None,
+            "updated_at": self.updated_at.isoformat() if self.updated_at else None,
+            "mailbox_count": len(self.mailboxes) if self.mailboxes else 0
+        } 

old/app/models/email.py

@@ -0,0 +1,148 @@
+import os
+import json
+from sqlalchemy import Column, Integer, String, Text, DateTime, ForeignKey, Boolean, JSON
+from sqlalchemy.orm import relationship
+from datetime import datetime
+import re
+import sys
+import logging
+
+from . import Base
+import config
+active_config = config.active_config
+
+
+class Email(Base):
+    """电子邮件模型"""
+    __tablename__ = 'emails'
+    
+    id = Column(Integer, primary_key=True)
+    mailbox_id = Column(Integer, ForeignKey('mailboxes.id'), nullable=False, index=True)
+    sender = Column(String(255), nullable=False)
+    recipients = Column(String(1000), nullable=False)
+    subject = Column(String(500), nullable=True)
+    body_text = Column(Text, nullable=True)
+    body_html = Column(Text, nullable=True)
+    received_at = Column(DateTime, default=datetime.utcnow)
+    read = Column(Boolean, default=False)
+    headers = Column(JSON, nullable=True)
+    
+    # 提取的验证码和链接
+    verification_code = Column(String(100), nullable=True)
+    verification_link = Column(String(1000), nullable=True)
+    
+    # 关联关系
+    mailbox = relationship("Mailbox", back_populates="emails")
+    attachments = relationship("Attachment", back_populates="email", cascade="all, delete-orphan")
+    
+    def save_raw_email(self, raw_content):
+        """保存原始邮件内容到文件"""
+        storage_path = active_config.MAIL_STORAGE_PATH
+        mailbox_dir = os.path.join(storage_path, str(self.mailbox_id))
+        os.makedirs(mailbox_dir, exist_ok=True)
+        
+        # 保存原始邮件内容
+        file_path = os.path.join(mailbox_dir, f"{self.id}.eml")
+        with open(file_path, 'wb') as f:
+            f.write(raw_content)
+    
+    def extract_verification_data(self):
+        """
+        尝试从邮件内容中提取验证码和验证链接
+        这个方法会在邮件保存时自动调用
+        """
+        logger = logging.getLogger(__name__)
+        
+        # 合并文本和HTML内容用于搜索
+        content = f"{self.subject or ''} {self.body_text or ''} {self.body_html or ''}"
+        logger.info(f"开始提取邮件ID={self.id}的验证信息，内容长度={len(content)}")
+        
+        # 首先检查是否是Cursor验证邮件
+        if "Verify your email" in self.subject and (
+            "cursor.sh" in self.sender.lower() or 
+            "cursor" in self.sender.lower()
+        ):
+            logger.info("检测到Cursor验证邮件")
+            # 从HTML中提取6位数字验证码
+            cursor_patterns = [
+                r'(\d{6})</div>',  # 匹配Cursor邮件中的6位数字验证码格式
+                r'<div[^>]*>(\d{6})</div>',  # 更宽松的匹配
+                r'>(\d{6})<',      # 最简单的形式
+                r'(\d{6})'         # 任何6位数字
+            ]
+            
+            for pattern in cursor_patterns:
+                matches = re.findall(pattern, content)
+                if matches:
+                    self.verification_code = matches[0]
+                    logger.info(f"从Cursor邮件中提取到验证码: {self.verification_code}")
+                    break
+            
+            return
+        
+        # 提取可能的验证码（4-8位数字或字母组合）
+        code_patterns = [
+            r'\b([A-Z0-9]{4,8})\b',  # 大写字母和数字
+            r'验证码[：:]\s*([A-Z0-9]{4,8})',  # 中文格式
+            r'验证码是[：:]\s*([A-Z0-9]{4,8})',  # 中文格式2
+            r'code[：:]\s*([A-Z0-9]{4,8})',  # 英文格式
+            r'code is[：:]\s*([A-Z0-9]{4,8})',  # 英文格式2
+            r'code[：:]\s*<[^>]*>([A-Z0-9]{4,8})',  # HTML格式
+            r'<div[^>]*>([0-9]{4,8})</div>',  # HTML分隔的数字
+            r'<strong[^>]*>([A-Z0-9]{4,8})</strong>',  # 粗体验证码
+        ]
+        
+        for pattern in code_patterns:
+            matches = re.findall(pattern, content, re.IGNORECASE)
+            if matches:
+                # 过滤掉明显不是验证码的结果
+                filtered_matches = [m for m in matches if len(m) >= 4 and not m.lower() in ['code', 'verify', 'http', 'https']]
+                if filtered_matches:
+                    self.verification_code = filtered_matches[0]
+                    logger.info(f"提取到验证码: {self.verification_code}")
+                    break
+        
+        # 提取验证链接
+        link_patterns = [
+            r'https?://\S+(?:verify|confirm|activate)\S+',
+            r'https?://\S+(?:token|auth|account)\S+',
+        ]
+        
+        for pattern in link_patterns:
+            matches = re.findall(pattern, content, re.IGNORECASE)
+            if matches:
+                self.verification_link = matches[0]
+                logger.info(f"提取到验证链接: {self.verification_link}")
+                break
+                
+        # 如果没有找到验证码，但邮件主题暗示这是验证邮件
+        verify_subjects = ['verify', 'confirmation', 'activate', 'validation', '验证', '确认']
+        if not self.verification_code and any(subj in self.subject.lower() for subj in verify_subjects):
+            logger.info("根据主题判断这可能是验证邮件，但未能提取到验证码")
+            # 尝试从HTML中提取明显的数字序列
+            if self.body_html:
+                number_matches = re.findall(r'(\d{4,8})', self.body_html)
+                filtered_numbers = [n for n in number_matches if len(n) >= 4 and len(n) <= 8]
+                if filtered_numbers:
+                    self.verification_code = filtered_numbers[0]
+                    logger.info(f"从HTML中提取到可能的验证码: {self.verification_code}")
+                    
+        logger.info(f"验证信息提取完成: code={self.verification_code}, link={self.verification_link}")
+    
+    def __repr__(self):
+        return f"<Email {self.id}: {self.subject}>"
+    
+    def to_dict(self):
+        """转换为字典，用于API响应"""
+        return {
+            "id": self.id,
+            "mailbox_id": self.mailbox_id,
+            "sender": self.sender,
+            "recipients": self.recipients,
+            "subject": self.subject,
+            "received_at": self.received_at.isoformat() if self.received_at else None,
+            "read": self.read,
+            "verification_code": self.verification_code,
+            "verification_link": self.verification_link,
+            "has_attachments": len(self.attachments) > 0 if self.attachments else False
+        } 

old/app/models/mailbox.py

@@ -0,0 +1,50 @@
+from sqlalchemy import Column, Integer, String, Boolean, DateTime, ForeignKey
+from sqlalchemy.orm import relationship
+from datetime import datetime
+import secrets
+
+from . import Base
+
+
+class Mailbox(Base):
+    """邮箱模型"""
+    __tablename__ = 'mailboxes'
+    
+    id = Column(Integer, primary_key=True)
+    address = Column(String(255), unique=True, nullable=False, index=True)
+    domain_id = Column(Integer, ForeignKey('domains.id'), nullable=False)
+    password_hash = Column(String(255), nullable=True)
+    description = Column(String(500), nullable=True)
+    active = Column(Boolean, default=True)
+    api_key = Column(String(64), unique=True, default=lambda: secrets.token_hex(16))
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    last_accessed = Column(DateTime, nullable=True)
+    
+    # 关系
+    domain = relationship("Domain", back_populates="mailboxes")
+    emails = relationship("Email", back_populates="mailbox", cascade="all, delete-orphan")
+    
+    @property
+    def full_address(self):
+        """获取完整邮箱地址 (包含域名)"""
+        return f"{self.address}@{self.domain.name}"
+    
+    def __repr__(self):
+        return f"<Mailbox {self.full_address}>"
+    
+    def to_dict(self):
+        """转换为字典，用于API响应"""
+        return {
+            "id": self.id,
+            "address": self.address,
+            "domain_id": self.domain_id,
+            "domain_name": self.domain.name if self.domain else None,
+            "full_address": self.full_address,
+            "description": self.description,
+            "active": self.active,
+            "created_at": self.created_at.isoformat() if self.created_at else None,
+            "updated_at": self.updated_at.isoformat() if self.updated_at else None,
+            "last_accessed": self.last_accessed.isoformat() if self.last_accessed else None,
+            "email_count": len(self.emails) if self.emails else 0
+        }