Created
October 16, 2022 18:54
-
-
Save Terkwood/dbed79d82e2a7304a50c820f444a455d to your computer and use it in GitHub Desktop.
emoji-friendly iterator over chars
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/// https://stackoverflow.com/a/50396438 | |
/// https://stackoverflow.com/questions/47193584/is-there-an-owned-version-of-stringchars | |
use std::io::{BufRead, BufReader, Read}; | |
use std::vec::IntoIter; | |
struct Chunks { | |
remaining: IntoIter<char>, | |
} | |
impl Chunks { | |
fn new(s: String) -> Self { | |
Chunks { | |
remaining: s.chars().collect::<Vec<_>>().into_iter(), | |
} | |
} | |
} | |
fn reader_chars<R: Read>(rdr: R) -> impl Iterator<Item = char> { | |
// We use 6 bytes here to force emoji to be segmented for demo purposes | |
// Pick more appropriate size for your case | |
let reader = BufReader::with_capacity(6, rdr); | |
reader | |
.lines() | |
.flat_map(|l| l) // Ignoring any errors | |
.flat_map(|s| Chunks::new(s).remaining) // from https://stackoverflow.com/q/47193584/155423 | |
} | |
fn main() { | |
// emoji are 4 bytes each | |
let data = "😻🧐🐪💩a1.💐\nf😃"; | |
let data = data.as_bytes(); | |
for c in reader_chars(data) { | |
println!(">{}<", c); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment