fanlusky
a7779d2b05
`vendor/MetasequoiaImeEngine` submodule 改为 `engine/` 目录，导入的是 product-lock.json 原本钉住的提交 c810d201，逐文件核对过 blob，因此这是一次 搬迁而不是引擎升级。引擎自己的嵌套 submodule（googlepinyinime-rev、utfcpp、 miniaudio）按各自 gitlink 一并展开，来源与提交见 engine/UPSTREAM.md。 Windows 专门化裁掉了不属于本产品的部分：whisper.cpp 与本地推理 provider、 macOS 示例宿主、整个 dictionary/ 建库流水线、上游 CI 与 release-please 配置。 词库仍按 product-lock.json 在构建时取发布产物。 引擎不再进 product-lock.json：没有 gitlink 就没有可比对的东西，锁里写一个上游 commit 等于宣称这棵树仍等于上游，而第一个 Windows 专门化改动落地时这句话就假了。 verify-contracts / verify-checkout 随之移除，verify-published 保留。 CI 与工具链：引擎源码并入根 scripts/format.sh（删掉引擎自己的那份，避免两套排除 列表分叉）；引擎 voice.yml 里的 silero_vad.onnx 摘要校验移到本仓 lock job； engine-bump-triage 工作流与其测试删除；gitsubmodule 的 dependabot 频率由 daily 改为 monthly。 README、README.en、AGENTS.md、CONTRIBUTING、docs/product-release.md 及各子目录 文档同步说明新的位置与边界。
121 lines
3.0 KiB
C++
121 lines
3.0 KiB
C++
#include "wubi_scheme.h"
|
|
#include <algorithm>
|
|
#include <cctype>
|
|
|
|
namespace
|
|
{
|
|
bool is_wubi_letter(char lower, bool mixed_pinyin_allowed)
|
|
{
|
|
return (lower >= 'a' && lower <= 'y') || (mixed_pinyin_allowed && lower == 'z');
|
|
}
|
|
|
|
bool is_wubi_vk(ImeKeyCode vk, bool mixed_pinyin_allowed)
|
|
{
|
|
return vk >= 'A' && vk <= 'Z' && is_wubi_letter(static_cast<char>(vk + ('a' - 'A')), mixed_pinyin_allowed);
|
|
}
|
|
|
|
std::string normalize_wubi_code(const std::string &input, size_t max_length, bool mixed_pinyin_allowed)
|
|
{
|
|
std::string normalized;
|
|
normalized.reserve((std::min)(input.size(), max_length));
|
|
for (const unsigned char ch : input)
|
|
{
|
|
const char lower = static_cast<char>(std::tolower(ch));
|
|
if (!is_wubi_letter(lower, mixed_pinyin_allowed))
|
|
{
|
|
continue;
|
|
}
|
|
normalized.push_back(lower);
|
|
if (normalized.size() == max_length)
|
|
{
|
|
break;
|
|
}
|
|
}
|
|
return normalized;
|
|
}
|
|
} // namespace
|
|
|
|
void WubiScheme::reset()
|
|
{
|
|
raw_input_.clear();
|
|
key_strokes_.clear();
|
|
extended_length_allowed_ = false;
|
|
}
|
|
|
|
void WubiScheme::handle_key(ImeKeyCode vk, ImeModifierMask modifiers_down, ImeCharacter wch)
|
|
{
|
|
if (vk == ImeKey::Backspace)
|
|
{
|
|
if (!raw_input_.empty())
|
|
{
|
|
raw_input_.pop_back();
|
|
}
|
|
if (!key_strokes_.empty())
|
|
{
|
|
key_strokes_.pop_back();
|
|
}
|
|
return;
|
|
}
|
|
|
|
if (vk == ImeKey::Escape || vk == ImeKey::Return)
|
|
{
|
|
reset();
|
|
return;
|
|
}
|
|
|
|
if (!is_wubi_vk(vk, mixed_pinyin_allowed_) || raw_input_.size() >= max_code_length())
|
|
{
|
|
return;
|
|
}
|
|
|
|
key_strokes_.push_back(KeyStroke{vk, modifiers_down, wch});
|
|
raw_input_.push_back(static_cast<char>(vk + ('a' - 'A')));
|
|
}
|
|
|
|
void WubiScheme::set_raw_input(const std::string &raw_input, const std::string &raw_input_with_cases)
|
|
{
|
|
raw_input_ = normalize_wubi_code(raw_input_with_cases.empty() ? raw_input : raw_input_with_cases, max_code_length(),
|
|
mixed_pinyin_allowed_);
|
|
key_strokes_.clear();
|
|
}
|
|
|
|
void WubiScheme::set_extended_length_allowed(bool allowed)
|
|
{
|
|
extended_length_allowed_ = allowed;
|
|
}
|
|
|
|
void WubiScheme::set_mixed_pinyin_allowed(bool allowed)
|
|
{
|
|
mixed_pinyin_allowed_ = allowed;
|
|
}
|
|
|
|
size_t WubiScheme::max_code_length() const
|
|
{
|
|
return extended_length_allowed_ ? kMaxMixedCodeLength : kMaxCodeLength;
|
|
}
|
|
|
|
QueryRequest WubiScheme::build_request() const
|
|
{
|
|
QueryRequest request;
|
|
request.scheme = type();
|
|
request.raw_input = raw_input_;
|
|
request.raw_input_with_cases = raw_input_;
|
|
request.normalized_input = raw_input_;
|
|
request.raw_segmentation = raw_input_;
|
|
request.normalized_segmentation = raw_input_;
|
|
request.segmentation = raw_input_;
|
|
request.key_strokes = key_strokes_;
|
|
request.valid = !raw_input_.empty();
|
|
return request;
|
|
}
|
|
|
|
std::string WubiScheme::get_preedit() const
|
|
{
|
|
return raw_input_;
|
|
}
|
|
|
|
SchemeType WubiScheme::type() const
|
|
{
|
|
return SchemeType::Wubi;
|
|
}
|