24024
af7c11d7f9
- 新增图像生成接口，支持试用、积分和自定义API Key模式 - 实现生成图片结果异步上传至MinIO存储，带重试机制 - 优化积分预扣除和异常退还逻辑，保障用户积分准确 - 添加获取生成历史记录接口，支持时间范围和分页 - 提供本地字典配置接口，支持模型、比例、提示模板和尺寸 - 实现图片批量上传接口，支持S3兼容对象存储 feat(admin): 增加管理员角色管理与权限分配接口 - 实现角色列表查询、角色创建、更新及删除功能 - 增加权限列表查询接口 - 实现用户角色分配接口，便于统一管理用户权限 - 增加系统字典增删查改接口，支持分类过滤和排序 - 权限控制全面覆盖管理接口，保证安全访问 feat(auth): 完善用户登录注册及权限相关接口与页面 - 实现手机号验证码发送及校验功能，保障注册安全 - 支持手机号注册、登录及退出接口，集成日志记录 - 增加修改密码功能，验证原密码后更新 - 提供动态导航菜单接口，基于权限展示不同菜单 - 实现管理界面路由及日志、角色、字典管理页面访问权限控制 - 添加系统日志查询接口，支持关键词和等级筛选 feat(app): 初始化Flask应用并配置蓝图与数据库 - 创建应用程序工厂，加载配置，初始化数据库和Redis客户端 - 注册认证、API及管理员蓝图，整合路由 - 根路由渲染主页模板 - 应用上下文中自动创建数据库表，保证运行环境准备完毕 feat(database): 提供数据库创建与迁移支持脚本 - 新增数据库创建脚本，支持自动检测是否已存在 - 添加数据库表初始化脚本，支持创建和删除所有表 - 实现RBAC权限初始化，包含基础权限和角色创建 - 新增字段手动修复脚本，添加用户API Key和积分字段 - 强制迁移脚本支持清理连接和修复表结构，初始化默认数据及角色分配 feat(config): 新增系统配置参数 - 配置数据库、Redis、Session和MinIO相关参数 - 添加AI接口地址及试用Key配置 - 集成阿里云短信服务配置及开发模式相关参数 feat(extensions): 初始化数据库、Redis和MinIO客户端 - 创建全局SQLAlchemy数据库实例和Redis客户端 - 配置基于boto3的MinIO兼容S3客户端 chore(logs): 添加示例系统日志文件 - 记录用户请求、验证码发送成功与失败的日志信息
81 lines
2.7 KiB
Python
81 lines
2.7 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
from warnings import warn
|
|
|
|
from .api import from_bytes
|
|
from .constant import CHARDET_CORRESPONDENCE, TOO_SMALL_SEQUENCE
|
|
|
|
# TODO: remove this check when dropping Python 3.7 support
|
|
if TYPE_CHECKING:
|
|
from typing_extensions import TypedDict
|
|
|
|
class ResultDict(TypedDict):
|
|
encoding: str | None
|
|
language: str
|
|
confidence: float | None
|
|
|
|
|
|
def detect(
|
|
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
|
|
) -> ResultDict:
|
|
"""
|
|
chardet legacy method
|
|
Detect the encoding of the given byte string. It should be mostly backward-compatible.
|
|
Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
|
|
This function is deprecated and should be used to migrate your project easily, consult the documentation for
|
|
further information. Not planned for removal.
|
|
|
|
:param byte_str: The byte sequence to examine.
|
|
:param should_rename_legacy: Should we rename legacy encodings
|
|
to their more modern equivalents?
|
|
"""
|
|
if len(kwargs):
|
|
warn(
|
|
f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
|
|
)
|
|
|
|
if not isinstance(byte_str, (bytearray, bytes)):
|
|
raise TypeError( # pragma: nocover
|
|
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
|
|
)
|
|
|
|
if isinstance(byte_str, bytearray):
|
|
byte_str = bytes(byte_str)
|
|
|
|
r = from_bytes(byte_str).best()
|
|
|
|
encoding = r.encoding if r is not None else None
|
|
language = r.language if r is not None and r.language != "Unknown" else ""
|
|
confidence = 1.0 - r.chaos if r is not None else None
|
|
|
|
# automatically lower confidence
|
|
# on small bytes samples.
|
|
# https://github.com/jawah/charset_normalizer/issues/391
|
|
if (
|
|
confidence is not None
|
|
and confidence >= 0.9
|
|
and encoding
|
|
not in {
|
|
"utf_8",
|
|
"ascii",
|
|
}
|
|
and r.bom is False # type: ignore[union-attr]
|
|
and len(byte_str) < TOO_SMALL_SEQUENCE
|
|
):
|
|
confidence -= 0.2
|
|
|
|
# Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
|
|
# but chardet does return 'utf-8-sig' and it is a valid codec name.
|
|
if r is not None and encoding == "utf_8" and r.bom:
|
|
encoding += "_sig"
|
|
|
|
if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
|
|
encoding = CHARDET_CORRESPONDENCE[encoding]
|
|
|
|
return {
|
|
"encoding": encoding,
|
|
"language": language,
|
|
"confidence": confidence,
|
|
}
|