Jia Sui fc3564e4d9 feat(engine): 生成式纠错空间兜静态表长尾
静态纠错表四类形状(相邻换位/漏字/QWERTY 邻键替换/限重复邻键插入)均为
穷举式生成,表外单编辑手误(非相邻键替换、任意字母插入)结构性无人管——
这是覆盖反馈的机制根源。新增生成式索引:对全部合法音节枚举表外形状
(48,216 对,首次纠错查询时一次性构建),并入纠错索引,k-best/贵档垫底/
上下文消解全链路复用;换位/漏字静态已穷尽,不枚举。

表内零回归为结构性保证:含生成边的切分在 k-best 排序中整体垫底
(has_generated 先序键),最优切分为纯静态时全部生成切分被丢弃——丢弃
规则在 autocorrect_cut_kbest 单点实现,主解析与 head+简拼尾组合路径同享;
生成读法只在静态空间完全无法解释输入时出场。混表加权仲裁依赖训练权重,
留给方向阶段 3。

评测:eval 新增 outside 注错档(表外形状,与静态表构造性不相交),覆盖
增益量化 R@1 47.7/44.3/36.3/22.7(四率;静态-only 恒为 0);表内四档
R@1/R@3 与基线逐位一致;种子聚合不回归。fixture 四用例含 head 组合路径
判别(shatngzh)。README 补 outside 档与资源目录说明。
2026-10-04 01:27:15 +08:00
2026-09-30 19:58:18 +08:00
2026-09-09 04:05:24 +09:00
2025-11-10 21:10:23 +08:00

Metasequoia IME for Windows

中文 README · Website · Docs · Privacy · Code signing policy

CI CodeQL Release Downloads License Stars

A free and open-source Chinese and Japanese input method for Windows 10 and 11, built on TSF with no legacy IMM32 path.

This repository is the whole Windows product: the TSF text service DLL, the resident server, the conversion engine, a self-written native GUI framework, the HTML surfaces and the installer. The engine was imported from MSIME-Engine and specialized for Windows; it now lives in engine/ as a first-party component, so a plain clone builds the product. See engine/UPSTREAM.md.

This is a public beta. Expect rough edges and read the release notes before upgrading.

Install

Download the installer from Releases or the download page, run it, then switch with Win + Space.

Current builds are not code signed. SmartScreen will block them and uiAccess is unavailable, which means the candidate window cannot float above elevated applications. Verify the download with the SHA256 published on the download page.

You need the Microsoft Visual C++ 2015–2022 Redistributable (x64). The server and settings app are 64-bit; the x86 redistributable is a separate package and does not substitute for it. If you cannot switch to the IME, the server keeps exiting, or the settings window closes immediately, install that first.

What it does

  • Chinese input: full pinyin, double pinyin (Xiaohe / Ziranma / Shoudao / Microsoft / Sogou / Ziguang / Zhineng ABC / Guobiao / Pinyin Jiajia), Wubi 86
  • Japanese input: romaji, with hiragana, katakana and dictionary candidates; also available as a temporary mode from Chinese
  • Helpcode (形码) filtering on pinyin schemes: six tables, single- and double-code
  • Optional cloud candidates, and AI suggestions via DeepSeek / OpenAI / SiliconFlow / Groq
  • English-Chinese glosses in the vertical candidate window
  • Mixed Chinese-English input, emoji and kaomoji, a dedicated English candidate mode
  • Local input statistics (off by default): character counts and active time stay on this machine; view and clean them under Settings → Statistics
  • Voice input with streaming recognition and optional cleanup
  • Handwriting, on-screen keyboard, floating toolbar, clipboard history
  • User dictionary management, candidate frequency tuning, skins with light and dark variants

Privacy

An input method sees every keystroke, so the boundaries are stated explicitly in PRIVACY.md: which features reach the network, what each one sends, what the defaults are, and how to turn each off.

Two things worth knowing up front. Cloud candidates are on by default — the composition spelling goes to Google's input-tools service, and it is the only network feature that works without you supplying a credential. API tokens are stored in plain text in config.toml, unlike macOS and Linux which use the Keychain and Secret Service.

There is no telemetry, analytics or crash reporting of any kind.

Building and contributing

CONTRIBUTING.md has the environment, the build order and what to run before opening a pull request. Contributions do not have to be code — dictionary entries, documentation, icons and compatibility testing all count, and the recruiting page lists them by area.

Note that most issues, documentation and code comments are in Chinese. English pull requests and issues are welcome.

Code signing policy

Free code signing provided by SignPath.io, certificate by SignPath Foundation.

What is signed, who the committers, reviewers and approvers are, the build and release process and the current status are in the code signing policy. The privacy policy is PRIVACY.md.

Licence

GPL-3.0. See LICENSE and THIRD_PARTY_NOTICES.txt.

S
Description
水杉输入法 Windows 产品:TSF、Server、GUI、设置页与安装器。内测:tg: https://t.me/msimegroup QQ Group: 829919142
https://msime.app
Readme GPL-3.0
24 MiB
0 Stars 1 Watchers 0 Forks
Languages
C++ 93.5%
Python 2.4%
PowerShell 2%
CMake 0.9%
Inno Setup 0.7%
Other 0.5%