这是indexloc提供的服务，不要输入任何密码
Skip to content

Support multi languages #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 3, 2025
Merged

Support multi languages #5

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a18e43
Support multi languages
mosuka Jun 3, 2025
2a11420
Fix document
mosuka Jun 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 19 additions & 29 deletions src/segmenter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,38 +19,26 @@ impl Segmenter {
/// A new Segmenter instance with the specified or default AdaBoost learner.
pub fn new(learner: Option<AdaBoost>) -> Self {
let patterns = vec![
// Numbers
(Regex::new(r"[0-9０-９]").unwrap(), "N"),
// Japanese Kanji numbers
(Regex::new(r"[一二三四五六七八九十百千万億兆]").unwrap(), "M"),
// Japanese Kanji
(Regex::new(r"[一-龠々〆ヵヶ]").unwrap(), "H"),
// Japanese Hiragana
// Hiragana (Japanese)
(Regex::new(r"[ぁ-ん]").unwrap(), "I"),
// Japanese Katakana
(Regex::new(r"[ァ-ヴーｱ-ﾝﾞｰ]").unwrap(), "K"),
// Latin alphabet (ASCII + full-width)
// Katakana (Japanese)
(Regex::new(r"[ァ-ヴーｱ-ﾝﾞﾟ]").unwrap(), "K"),
// Hangul (Korean)
(Regex::new(r"[가-힣]").unwrap(), "G"),
// Thai script
(Regex::new(r"[ก-๛]").unwrap(), "T"),
// Kanji (Japanese)
(Regex::new(r"[一-龠々〆ヵヶ]").unwrap(), "H"),
// Kanji (CJK Unified Ideographs)
(Regex::new(r"[㐀-䶵一-鿿]").unwrap(), "Z"),
// Extended Latin (Vietnamese, etc.)
(Regex::new(r"[À-ÿĀ-ſƀ-ƿǍ-ɏ]").unwrap(), "E"),
// ASCII + Full-width Latin
(Regex::new(r"[a-zA-Zａ-ｚＡ-Ｚ]").unwrap(), "A"),
// Numbers (ASCII + full-width)
(Regex::new(r"[0-9０-９]").unwrap(), "N"),
// // Japanese Kanji numbers
// (Regex::new(r"[一二三四五六七八九十百千万億兆]").unwrap(), "M"),
// // Japanese Kanji
// (Regex::new(r"[一-龠々〆ヵヶ]").unwrap(), "J"),
// // Chinese Kanji (CJK Unified Ideographs)
// (Regex::new(r"[㐀-䶵一-鿿]").unwrap(), "M"),
// // Hangul (Korean)
// (Regex::new(r"[가-힣]").unwrap(), "K"),
// // Hiragana (Japanese)
// (Regex::new(r"[ぁ-ん]").unwrap(), "I"),
// // Katakana (Japanese)
// (Regex::new(r"[ァ-ヴーｱ-ﾝﾞﾟ]").unwrap(), "K"),
// // Latin alphabet (ASCII + full-width)
// (Regex::new(r"[a-zA-Zａ-ｚＡ-Ｚ]").unwrap(), "A"),
// // Numbers (ASCII + full-width)
// (Regex::new(r"[0-9０-９]").unwrap(), "N"),
// // Vietnamese Extended Latin
// (Regex::new(r"[À-ſ]").unwrap(), "V"),
// // Thai script
// (Regex::new(r"[ก-๛]").unwrap(), "T"),
];

Segmenter {
Expand All @@ -65,7 +53,9 @@ impl Segmenter {
/// * `ch` - A string slice representing a single character.
///
/// # Returns
/// A static string representing the type of the character, such as "M", "H", "I", "K", "A", "N", or "O" (for others).
/// A string slice representing the type of the character, such as "N" for number,
/// "I" for Hiragana, "K" for Katakana, etc. If the character does not match any pattern,
/// it returns "O" for Other.
pub fn get_type(&self, ch: &str) -> &str {
for (pattern, label) in &self.patterns {
if pattern.is_match(ch) {
Expand Down