tiebameow 0.2.8__py3-none-any.whl

tiebameow/schemas/fragments.py

@@ -0,0 +1,188 @@
+from typing import Literal, Protocol, get_args, runtime_checkable
+
+from pydantic import BaseModel, field_validator
+
+
+class FragAtModel(BaseModel):
+    """@碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'at'
+        text (str): 被@用户的昵称 含@
+        user_id (int): 被@用户的user_id
+    """
+
+    type: Literal["at"] = "at"
+    text: str = ""
+    user_id: int = 0
+
+
+class FragEmojiModel(BaseModel):
+    """表情碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'emoji'
+        id (str): 表情图片id
+        desc (str): 表情描述
+    """
+
+    type: Literal["emoji"] = "emoji"
+    id: str = ""
+    desc: str = ""
+
+
+class FragImageModel(BaseModel):
+    """图像碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'image'
+        src (str): 小图链接 宽720px
+        big_src (str): 大图链接 宽960px
+        origin_src (str): 原图链接
+        origin_size (int): 原图大小（字节）
+        show_width (int): 图像在客户端预览显示的宽度（像素）
+        show_height (int): 图像在客户端预览显示的高度（像素）
+        hash (str): 百度图床hash
+    """
+
+    type: Literal["image"] = "image"
+    src: str = ""
+    big_src: str = ""
+    origin_src: str = ""
+    origin_size: int = 0
+    show_width: int = 0
+    show_height: int = 0
+    hash: str = ""
+
+
+class FragItemModel(BaseModel):
+    """item碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'item'
+        text (str): item名称
+    """
+
+    type: Literal["item"] = "item"
+    text: str = ""
+
+
+class FragLinkModel(BaseModel):
+    """链接碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'link'
+        text (str): 原链接
+        title (str): 链接标题
+        raw_url (str): 解析后的原链接
+    """
+
+    type: Literal["link"] = "link"
+    text: str = ""
+    title: str = ""
+    raw_url: str = ""
+
+    @field_validator("raw_url", mode="before")
+    @classmethod
+    def _coerce_raw_url(cls, v: str | None) -> str:
+        return "" if v is None else str(v)
+
+
+class FragTextModel(BaseModel):
+    """纯文本碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'text'
+        text (str): 文本内容
+    """
+
+    type: Literal["text"] = "text"
+    text: str = ""
+
+
+class FragTiebaPlusModel(BaseModel):
+    """贴吧plus广告碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'tieba_plus'
+        text (str): 贴吧plus广告描述
+        url (str): 解析后的贴吧plus广告跳转链接
+    """
+
+    type: Literal["tieba_plus"] = "tieba_plus"
+    text: str = ""
+    url: str = ""
+
+    @field_validator("url", mode="before")
+    @classmethod
+    def _coerce_url(cls, v: str | None) -> str:
+        return "" if v is None else str(v)
+
+
+class FragVideoModel(BaseModel):
+    """视频碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'video'
+        src (str): 视频链接
+        cover_src (str): 封面链接
+        duration (int): 视频长度（秒）
+        width (int): 视频宽度（像素）
+        height (int): 视频高度（像素）
+        view_num (int): 浏览次数
+    """
+
+    type: Literal["video"] = "video"
+    src: str = ""
+    cover_src: str = ""
+    duration: int = 0
+    width: int = 0
+    height: int = 0
+    view_num: int = 0
+
+
+class FragVoiceModel(BaseModel):
+    """音频碎片模型。
+
+    Attributes:
+        type: 片段类型，固定为'voice'
+        md5 (str): 音频md5
+        duration (int): 音频长度（秒）
+    """
+
+    type: Literal["voice"] = "voice"
+    md5: str = ""
+    duration: int = 0
+
+
+class FragUnknownModel(BaseModel):
+    """未知碎片模型。"""
+
+    type: Literal["unknown"] = "unknown"
+    raw_data: str = ""
+
+
+Fragment = (
+    FragAtModel
+    | FragEmojiModel
+    | FragImageModel
+    | FragItemModel
+    | FragLinkModel
+    | FragTextModel
+    | FragTiebaPlusModel
+    | FragVideoModel
+    | FragVoiceModel
+    | FragUnknownModel
+)
+
+
+@runtime_checkable
+class TypeFragText(Protocol):
+    text: str
+
+
+FRAG_MAP: dict[str, type[Fragment]] = {
+    key: cls
+    for cls in get_args(Fragment)
+    for key in (cls.__name__.removesuffix("Model"), cls.model_fields["type"].default)
+}

tiebameow/schemas/rules.py

@@ -0,0 +1,247 @@
+from __future__ import annotations
+
+from enum import StrEnum, unique
+from typing import Any, Self
+
+from pydantic import BaseModel, Field, model_validator
+
+
+@unique
+class FieldType(StrEnum):
+    """
+    支持的字段类型枚举。
+
+    定义了规则引擎中可用于条件判断的所有字段，包括主题帖(Thread)、回复(Post)、
+    用户信息以及各类型的通用属性。
+    """
+
+    TITLE = "title"  # 仅Thread
+    IS_GOOD = "is_good"  # 仅Thread
+    IS_TOP = "is_top"  # 仅Thread
+    IS_SHARE = "is_share"  # 仅Thread
+    IS_HIDE = "is_hide"  # 仅Thread
+    TEXT = "text"
+    FULL_TEXT = "full_text"
+    ATS = "ats"
+    LEVEL = "author.level"
+    USER_ID = "author.user_id"
+    PORTRAIT = "author.portrait"
+    USER_NAME = "author.user_name"
+    NICK_NAME = "author.nick_name"
+    AGREE_NUM = "agree_num"
+    DISAGREE_NUM = "disagree_num"
+    REPLY_NUM = "reply_num"  # 仅Thread/Post
+    VIEW_NUM = "view_num"  # 仅Thread
+    SHARE_NUM = "share_num"  # 仅Thread
+    CREATE_TIME = "create_time"
+    LAST_TIME = "last_time"  # 仅Thread
+    SHARE_FNAME = "share_origin.fname"  # 仅Thread
+    SHARE_FID = "share_origin.fid"  # 仅Thread
+    SHARE_TITLE = "share_origin.title"  # 仅Thread
+    SHARE_TEXT = "share_origin.text"  # 仅Thread
+
+
+@unique
+class OperatorType(StrEnum):
+    """
+    支持的操作符类型枚举。
+
+    定义了字段值与目标值进行比较的具体逻辑。
+    """
+
+    CONTAINS = "contains"
+    NOT_CONTAINS = "not_contains"
+    REGEX = "match"
+    NOT_REGEX = "not_match"
+    EQ = "eq"
+    NEQ = "neq"
+    GT = "gt"
+    LT = "lt"
+    GTE = "gte"
+    LTE = "lte"
+    IN = "in"
+    NOT_IN = "not_in"
+
+
+@unique
+class LogicType(StrEnum):
+    """
+    支持的逻辑运算符枚举。
+
+    用于连接多个条件节点，构成复杂的逻辑表达式。
+    """
+
+    AND = "AND"
+    OR = "OR"
+    NOT = "NOT"
+
+
+@unique
+class ActionType(StrEnum):
+    """
+    支持的动作类型枚举。
+
+    定义了规则匹配成功后只需执行的具体操作。
+    """
+
+    DELETE = "delete"
+    BAN = "ban"
+    NOTIFY = "notify"
+
+
+@unique
+class TargetType(StrEnum):
+    """
+    支持的规则目标类型枚举。
+
+    定义了规则适用的内容类型范围。
+    """
+
+    ALL = "all"
+    THREAD = "thread"
+    POST = "post"
+    COMMENT = "comment"
+
+
+class Condition(BaseModel):
+    """单个条件单元。
+
+    定义了规则中的最小匹配单元，包含字段、操作符和目标值。
+
+    Attributes:
+        field: 匹配字段路径，支持点号分隔的嵌套字段，如 'content', 'author.level'。
+        operator: 匹配操作符，支持 'contains', 'regex', 'eq', 'gt', 'lt', 'gte', 'lte', 'in'。
+        value: 匹配的目标值，类型取决于操作符。
+    """
+
+    field: FieldType
+    operator: OperatorType
+    value: Any
+
+
+class RuleGroup(BaseModel):
+    """规则组，支持逻辑组合。
+
+    用于组合多个条件或子规则组，支持 AND, OR, NOT 等逻辑运算。
+
+    Attributes:
+        logic: 逻辑关系，如 'AND', 'OR', 'NOT' 等。
+        conditions: 子条件列表，可以是 Condition 或嵌套的 RuleGroup。
+    """
+
+    logic: LogicType
+    conditions: list[RuleNode]
+
+
+# 递归类型别名
+type RuleNode = Condition | RuleGroup
+
+
+class DeleteAction(BaseModel):
+    """删除动作配置。"""
+
+    enabled: bool = False
+    params: dict[str, Any] = Field(default_factory=dict)
+
+
+class BanAction(BaseModel):
+    """封禁动作配置。"""
+
+    enabled: bool = False
+    days: int = Field(default=1, ge=1, le=10)
+    params: dict[str, Any] = Field(default_factory=dict)
+
+
+class NotifyAction(BaseModel):
+    """通知动作配置。"""
+
+    enabled: bool = False
+    template: str = ""
+    params: dict[str, Any] = Field(default_factory=dict)
+
+
+class Actions(BaseModel):
+    """匹配命中后的动作集合。
+
+    定义了当规则匹配成功时应执行的操作集合。
+    """
+
+    delete: DeleteAction = Field(default_factory=DeleteAction)
+    ban: BanAction = Field(default_factory=BanAction)
+    notify: NotifyAction = Field(default_factory=NotifyAction)
+
+
+class ReviewRule(BaseModel):
+    """完整的审查规则实体。
+
+    包含规则的元数据、触发条件逻辑树以及命中后的执行动作。
+
+    Attributes:
+        id: 规则唯一标识 ID。
+        fid: 贴吧 fid。
+        forum_rule_id: 吧内规则标识 ID。
+        uploader_id: 规则创建者的用户 ID。
+        target_type: 规则适用的目标类型，如 'all', 'thread', 'post', 'comment'。
+        name: 规则名称。
+        enabled: 是否启用该规则。
+        priority: 规则优先级，数字越大越先执行。
+        trigger: 规则触发条件的逻辑树根节点。
+        actions: 规则命中后执行的动作配置。
+    """
+
+    id: int
+    fid: int
+    forum_rule_id: int
+    uploader_id: int
+    target_type: TargetType
+    name: str
+    enabled: bool
+    priority: int
+    trigger: RuleNode
+    actions: Actions
+
+    @model_validator(mode="after")
+    def validate_trigger_match_target(self) -> Self:
+        """验证 trigger 中的字段是否匹配 target_type。"""
+
+        thread_only_fields = {
+            FieldType.TITLE,
+            FieldType.IS_GOOD,
+            FieldType.IS_TOP,
+            FieldType.IS_SHARE,
+            FieldType.IS_HIDE,
+            FieldType.VIEW_NUM,
+            FieldType.SHARE_NUM,
+            FieldType.LAST_TIME,
+            FieldType.SHARE_FNAME,
+            FieldType.SHARE_FID,
+            FieldType.SHARE_TITLE,
+            FieldType.SHARE_TEXT,
+        }
+
+        thread_post_fields = {FieldType.REPLY_NUM}
+
+        target = self.target_type
+
+        forbidden_fields: set[FieldType] = set()
+
+        if target == TargetType.POST:
+            forbidden_fields = thread_only_fields
+        elif target == TargetType.COMMENT:
+            forbidden_fields = thread_only_fields | thread_post_fields
+        elif target == TargetType.ALL:
+            forbidden_fields = thread_only_fields | thread_post_fields
+
+        if not forbidden_fields:
+            return self
+
+        def validate_node(node: RuleNode) -> None:
+            if isinstance(node, Condition):
+                if node.field in forbidden_fields:
+                    raise ValueError(f"Field '{node.field}' is not valid for target_type '{target}'")
+            elif isinstance(node, RuleGroup):
+                for child in node.conditions:
+                    validate_node(child)
+
+        validate_node(self.trigger)
+        return self

tiebameow/serializer/__init__.py

@@ -0,0 +1,15 @@
+from .serializer import (
+    deserialize,
+    deserialize_comment,
+    deserialize_post,
+    deserialize_thread,
+    serialize,
+)
+
+__all__ = [
+    "serialize",
+    "deserialize",
+    "deserialize_thread",
+    "deserialize_post",
+    "deserialize_comment",
+]

tiebameow/serializer/serializer.py

@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, Literal, overload
+
+from ..models.dto import CommentDTO, PostDTO, ThreadDTO
+
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
+__all__ = [
+    "serialize",
+    "deserialize",
+    "deserialize_thread",
+    "deserialize_post",
+    "deserialize_comment",
+]
+
+
+def serialize(obj: Any) -> Any:
+    """将对象序列化为 JSON 可用的字典或列表。"""
+    if hasattr(obj, "model_dump"):
+        return obj.model_dump(mode="json")
+    return obj
+
+
+def _normalize_contents(data: Any) -> list[Any]:
+    if isinstance(data, list):
+        return data
+    if isinstance(data, dict):
+        return data.get("objs", []) or []
+    return []
+
+
+def _normalize_user(data: dict[str, Any]) -> None:
+    if "author" not in data and "user" in data:
+        data["author"] = data["user"]
+
+
+def _preprocess_thread(data: Mapping[str, Any]) -> dict[str, Any]:
+    d = dict(data)
+    if "contents" in d:
+        d["contents"] = _normalize_contents(d["contents"])
+
+    _normalize_user(d)
+
+    if "share_origin" in d and isinstance(d["share_origin"], dict):
+        so = dict(d["share_origin"])
+        if "contents" in so:
+            so["contents"] = _normalize_contents(so["contents"])
+        d["share_origin"] = so
+
+    return d
+
+
+def _preprocess_post(data: Mapping[str, Any]) -> dict[str, Any]:
+    d = dict(data)
+    if "contents" in d:
+        d["contents"] = _normalize_contents(d["contents"])
+
+    _normalize_user(d)
+
+    if "comments" in d and isinstance(d["comments"], list):
+        d["comments"] = [_preprocess_comment(c) if isinstance(c, dict) else c for c in d["comments"]]
+
+    return d
+
+
+def _preprocess_comment(data: Mapping[str, Any]) -> dict[str, Any]:
+    d = dict(data)
+    if "contents" in d:
+        d["contents"] = _normalize_contents(d["contents"])
+
+    _normalize_user(d)
+
+    return d
+
+
+def deserialize_thread(data: Mapping[str, Any]) -> ThreadDTO:
+    """将 JSON/dict 反序列化为 ThreadDTO 对象。"""
+    return ThreadDTO.model_validate(_preprocess_thread(data))
+
+
+def deserialize_post(data: Mapping[str, Any]) -> PostDTO:
+    """将 JSON/dict 反序列化为 PostDTO 对象。"""
+    return PostDTO.model_validate(_preprocess_post(data))
+
+
+def deserialize_comment(data: Mapping[str, Any]) -> CommentDTO:
+    """将 JSON/dict 反序列化为 CommentDTO 对象。"""
+    return CommentDTO.model_validate(_preprocess_comment(data))
+
+
+@overload
+def deserialize(item_type: Literal["thread"], data: Mapping[str, Any]) -> ThreadDTO: ...
+
+
+@overload
+def deserialize(item_type: Literal["post"], data: Mapping[str, Any]) -> PostDTO: ...
+
+
+@overload
+def deserialize(item_type: Literal["comment"], data: Mapping[str, Any]) -> CommentDTO: ...
+
+
+def deserialize(
+    item_type: Literal["thread", "post", "comment"], data: Mapping[str, Any]
+) -> ThreadDTO | PostDTO | CommentDTO:
+    """根据类型进行通用反序列化。"""
+    if item_type == "thread":
+        return deserialize_thread(data)
+    if item_type == "post":
+        return deserialize_post(data)
+    if item_type == "comment":
+        return deserialize_comment(data)
+    raise ValueError(f"Unsupported item_type: {item_type}")

tiebameow/utils/logger.py

@@ -0,0 +1,129 @@
+import logging
+import sys
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+from loguru import logger
+
+if TYPE_CHECKING:
+    from types import FrameType
+
+__all__ = ["logger", "init_logger"]
+
+
+class InterceptHandler(logging.Handler):
+    """
+    拦截标准日志消息并将其路由到 Loguru。
+    """
+
+    def emit(self, record: logging.LogRecord) -> None:
+        try:
+            level: str | int = logger.level(record.levelname).name
+        except ValueError:
+            level = record.levelno
+
+        frame: FrameType | None = logging.currentframe()
+        depth = 2
+        while frame and frame.f_code.co_filename == logging.__file__:
+            frame = frame.f_back
+            depth += 1
+
+        logger.opt(depth=depth, exception=record.exc_info).log(level, record.getMessage())
+
+
+def init_logger(
+    *,
+    service_name: str = "tiebameow",
+    level: str = "INFO",
+    console_format: str | None = None,
+    enable_filelog: bool = False,
+    enable_error_filelog: bool = False,
+    log_dir: str | Path = "logs",
+    file_format: str | None = None,
+    rotation: str = "00:00",
+    retention: str = "14 days",
+    intercept_standard_logging: bool = True,
+    enqueue: bool = True,
+    diagnose: bool = True,
+    reset: bool = True,
+    add_console: bool = True,
+) -> None:
+    """
+    使用标准配置初始化适用于 TiebaMeow 服务的 loguru logger。
+
+    Args:
+        service_name: 服务名称，用于日志文件命名。
+
+        level: 最低日志级别（例如 "DEBUG", "INFO"）。
+        console_format: 控制台输出的自定义格式。
+        enable_filelog: 是否启用日志文件记录。
+        enable_error_filelog: 是否启用错误日志文件记录。
+        log_dir: 日志文件存储目录。
+        file_format: 文件输出的自定义格式。
+        rotation: 日志轮转条件（例如 "1 day", "500 MB", "00:00"）。
+        retention: 日志保留条件（例如 "10 days"）。
+        intercept_standard_logging: 是否拦截标准库日志。
+        enqueue: 是否使用线程安全的日志记录（异步安全）。
+        diagnose: 是否在异常回溯中显示变量值。
+        reset: 是否移除所有现有的处理器。如果集成到已有日志记录的应用中（例如 NoneBot），请设置为 False。
+        add_console: 是否添加控制台处理器。如果应用已经有一个，请设置为 False。
+    """
+    if console_format is None:
+        console_format = (
+            "<green>{time:YYYY-MM-DD HH:mm:ss}</green> "
+            "<level>[{level}]</level> "
+            "<cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> | "
+            "<level>{message}</level>"
+        )
+
+    if reset:
+        logger.remove()
+
+    if add_console:
+        logger.add(
+            sys.stderr,
+            format=console_format,
+            level=level,
+            enqueue=enqueue,
+            diagnose=diagnose,
+        )
+
+    if enable_filelog or enable_error_filelog:
+        if file_format is None:
+            file_format = "{time:YYYY-MM-DD HH:mm:ss} [{level}] {name}:{function}:{line} | {message}"
+
+        log_path = Path(log_dir)
+        try:
+            log_path.mkdir(parents=True, exist_ok=True)
+        except Exception:
+            logger.warning("Failed to create log directory: {}, file logging disabled.", log_path)
+            return
+
+        if enable_filelog:
+            logger.add(
+                log_path / f"{service_name}.log",
+                format=file_format,
+                level=level,
+                rotation=rotation,
+                retention=retention,
+                encoding="utf-8",
+                enqueue=enqueue,
+                compression="zip",
+                diagnose=diagnose,
+            )
+
+        if enable_error_filelog:
+            logger.add(
+                log_path / f"{service_name}.error.log",
+                format=file_format,
+                level="ERROR",
+                rotation=rotation,
+                retention=retention,
+                encoding="utf-8",
+                enqueue=enqueue,
+                compression="zip",
+                diagnose=diagnose,
+            )
+
+    if intercept_standard_logging:
+        logging.basicConfig(handlers=[InterceptHandler()], level=0, force=True)

tiebameow/utils/time_utils.py

@@ -0,0 +1,15 @@
+from datetime import datetime
+from zoneinfo import ZoneInfo
+
+__all__ = ["SHANGHAI_TZ", "now_with_tz"]
+
+SHANGHAI_TZ = ZoneInfo("Asia/Shanghai")
+
+
+def now_with_tz() -> datetime:
+    """返回带时区的当前时间。
+
+    Returns:
+        datetime: 上海时区的当前时间。
+    """
+    return datetime.now(SHANGHAI_TZ)