Lu Fan(SonnyCalcr)
3cd429b19d
符号数据改用 rime-wanxiang 的符号表与 typst/codex 符号名，源数据放在 msime-dictionary 的 sources/symbols/，替换原来的 piliapp 符号表。 - 建库：新增 symbols_db.py，生成表情面板用的 symbol_catalog（中文分类）和 S 模式、符号混输用的 symbol_code；剔除 wanxiang-unrenderable.txt 列出的 Windows 自带字体显示不了的符号，以及与 ① ❶ 看不出区别的 Dingbats 带圈数字 - 新增 scripts/check-symbol-rendering.py，用 Windows 字体生成上面的剔除清单 - Shift+S 进入符号模式，按万象分组码（xl、sx、szq）、数字读音（yi → 一 ① ⑴） 或符号名（alpha、infinity）检索 - 符号混输：整串精确等于编码时混入，首个紧跟首选；读得成拼音的编码只混数字 序号写法；双拼先按方案换算成全拼再查（小鹤 sj → san → ③） - 表情面板符号页：中文分类，搜索把整词命中的符号列在「最佳匹配」 - 配置：utility.symbol_mode（默认开）、general.symbol_mixed_input（默认关） Refs #795
111 lines
4.4 KiB
C++
111 lines
4.4 KiB
C++
#include "../contracts/assets/assets.h"
|
|
#include "symbol_query.h"
|
|
#include "local_database.h"
|
|
|
|
#include "../core/data_path.h"
|
|
|
|
#include <cstdint>
|
|
#include <memory>
|
|
#include <unordered_set>
|
|
|
|
namespace metasequoia::local_modes
|
|
{
|
|
namespace
|
|
{
|
|
struct StatementCloser
|
|
{
|
|
void operator()(sqlite3_stmt *statement) const
|
|
{
|
|
sqlite3_finalize(statement);
|
|
}
|
|
};
|
|
|
|
// 编码只有字母；统一转小写，非字母返回空串（查不到任何符号）。
|
|
std::string normalize_code(const std::string &code)
|
|
{
|
|
std::string lower;
|
|
lower.reserve(code.size());
|
|
for (const unsigned char character : code)
|
|
{
|
|
if (character >= 'a' && character <= 'z')
|
|
lower.push_back(static_cast<char>(character));
|
|
else if (character >= 'A' && character <= 'Z')
|
|
lower.push_back(static_cast<char>(character - 'A' + 'a'));
|
|
else
|
|
return {};
|
|
}
|
|
return lower;
|
|
}
|
|
|
|
LocalQueryResult query_failure(const char *diagnostic)
|
|
{
|
|
return {{}, std::string(diagnostic)};
|
|
}
|
|
|
|
// ?1 = 编码，?2 = 前缀上界，?3 = limit。返回 symbol 一列，同一符号只取排位最好的那行。
|
|
LocalQueryResult run_query(const std::string &code, const std::filesystem::path &database_path, const char *sql,
|
|
int limit)
|
|
{
|
|
const std::string lower = normalize_code(code);
|
|
if (lower.empty() || limit <= 0)
|
|
return {};
|
|
if (database_path.empty())
|
|
return query_failure("Symbol database is unavailable.");
|
|
const std::shared_ptr<sqlite3> database = open_local_database(database_path);
|
|
if (!database)
|
|
return query_failure("Symbol database is unavailable.");
|
|
|
|
sqlite3_stmt *raw_statement = nullptr;
|
|
if (sqlite3_prepare_v2(database.get(), sql, -1, &raw_statement, nullptr) != SQLITE_OK)
|
|
return query_failure("Symbol database could not be queried.");
|
|
const std::unique_ptr<sqlite3_stmt, StatementCloser> statement(raw_statement);
|
|
std::string upper_bound = lower;
|
|
upper_bound.push_back(static_cast<char>(0x7f));
|
|
// 前缀查询的同一符号可能挂在好几个编码下（a 与 ao、codex 的 alpha 与 Alpha），多取一些再去重。
|
|
const int fetch_limit = limit <= (1 << 20) ? limit * 4 : limit;
|
|
if (sqlite3_bind_text(statement.get(), 1, lower.c_str(), -1, SQLITE_TRANSIENT) != SQLITE_OK ||
|
|
sqlite3_bind_text(statement.get(), 2, upper_bound.c_str(), -1, SQLITE_TRANSIENT) != SQLITE_OK ||
|
|
sqlite3_bind_int(statement.get(), 3, fetch_limit) != SQLITE_OK)
|
|
return query_failure("Symbol database could not be queried.");
|
|
|
|
LocalQueryResult result;
|
|
std::unordered_set<std::string> seen;
|
|
int step_result = SQLITE_ROW;
|
|
while ((step_result = sqlite3_step(statement.get())) == SQLITE_ROW &&
|
|
result.candidates.size() < static_cast<std::size_t>(limit))
|
|
{
|
|
const auto *symbol = reinterpret_cast<const char *>(sqlite3_column_text(statement.get(), 0));
|
|
if (symbol == nullptr || !seen.insert(symbol).second)
|
|
continue;
|
|
result.candidates.emplace_back(lower, symbol, 0, CandidateSource::Symbol);
|
|
}
|
|
if (step_result != SQLITE_ROW && step_result != SQLITE_DONE)
|
|
return query_failure("Symbol database could not be queried.");
|
|
const std::size_t count = result.candidates.size();
|
|
for (std::size_t index = 0; index < count; ++index)
|
|
result.candidates[index].weight = static_cast<std::int64_t>(count - index);
|
|
return result;
|
|
}
|
|
} // namespace
|
|
|
|
LocalQueryResult query_symbols(const std::string &code, int limit)
|
|
{
|
|
return query_symbols(code, data_file_path(metasequoia::assets::other_dictionary), limit);
|
|
}
|
|
|
|
LocalQueryResult query_symbols(const std::string &code, const std::filesystem::path &database_path, int limit)
|
|
{
|
|
// 整串命中的编码排最前；其余前缀命中按编码长短，短的通常是这一类的总表（x 先出 xl 再出 xlc）。
|
|
constexpr const char *kSql = "SELECT symbol FROM symbol_code WHERE code>=?1 AND code<?2 "
|
|
"ORDER BY code IS NOT ?1,length(code),sort_order LIMIT ?3";
|
|
return run_query(code, database_path, kSql, limit);
|
|
}
|
|
|
|
LocalQueryResult query_mixed_symbols(const std::string &code, const std::filesystem::path &database_path, int limit)
|
|
{
|
|
constexpr const char *kSql = "SELECT symbol FROM symbol_code WHERE code=?1 AND code<?2 AND mixed=1 "
|
|
"ORDER BY sort_order LIMIT ?3";
|
|
return run_query(code, database_path, kSql, limit);
|
|
}
|
|
} // namespace metasequoia::local_modes
|