AustrianToast/jttg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support more graphemes

Browse Source
This commit is contained in:
AustrianToast 2024-12-13 17:33:32 +01:00
parent 2e28ce053f
commit b38d4f2430
Signed by: AustrianToast
GPG Key ID: FA59D02DC1947418
1 changed files with 25 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
src/main.rs
View File

@ -1,6 +1,18 @@
use std::env::args;
const KNOWN_GRAPHEMES: [&str; 10] = ["a", "i", "u", "e", "o", "ka", "ki", "ku", "ke", "ko"];
// TODO: add "n" and Digraphs
const KNOWN_GRAPHEMES: [&str; 73] = [
"a", "i", "u", "e", "o", "ka", "ki", "ku", "ke", "ko", "ga", "gi", "gu", "ge", "go", "sa",
"shi", "su", "se", "so", "za", "ji", "zu", "ze", "zo", "ta", "chi", "tsu", "te", "to", "da",
"ji", "zu", "de", "do", "na", "ni", "nu", "ne", "no", "ha", "hi", "fu", "he", "ho", "ba", "bi",
"bu", "be", "bo", "pa", "pi", "pu", "pe", "po", "ma", "mi", "mu", "me", "mo", "ya", "yu", "ye",
"yo", "ra", "ri", "ru", "re", "ro", "wa", "wi", "we", "wo",
];
// convert unicode japanese into the latin alphabet, which is necessary in order to use split_word()
fn romanize(word: String) -> String {
todo!();
}
// look at the first letter, if it exists in KNOWN_GRAPHEMES, then add to graphemes
// else look at the first and second letter, if that exists in KNOWN_GRAPHEMES, then add that to grapehemes
@ -14,19 +26,20 @@ fn split_word(word: String) -> Vec<String> {
Some(val) => String::from(val),
None => break,
};
dbg!(&grapheme);
let temp = grapheme.as_str();
if KNOWN_GRAPHEMES.contains(&temp) {
// TODO: figure out how to deal with 'n'
if KNOWN_GRAPHEMES.contains(&grapheme.as_str()) {
graphemes.push(grapheme);
} else {
grapheme.push(word_chars.next().unwrap());
match word_chars.next() {
Some(val) => grapheme.push(val),
None => panic!("word contains non japanese grapheme: {grapheme}"),
};
let temp = grapheme.as_str();
if KNOWN_GRAPHEMES.contains(&temp) {
if KNOWN_GRAPHEMES.contains(&grapheme.as_str()) {
graphemes.push(grapheme);
} else {
panic!("word contains non japanese grapheme: {grapheme}");
}
}
}
@ -48,6 +61,9 @@ fn main() {
None => panic!("how?!"),
};
// TODO: sanitise even further. check if input contains any illegal chars
// input should only contain a-z, A-Z or in the future Unicode japanese chars
println!("Sanitised input: {}", input);
let graphemes = split_word(input);