Created
July 19, 2020 15:03
-
-
Save rphsoftware/0e275005dd77eb4e15a875569f001dca to your computer and use it in GitHub Desktop.
File that generates a bitflag-based binary file containing what unicode characters are deemed uppercase (by the official Unicode Consortium document)
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
use std::{fs, env}; | |
use minidom::Element; | |
use std::fs::File; | |
use std::io::Write; | |
fn main() { | |
let mut a = env::current_dir().expect("Something went wrong"); | |
println!("{}", a.as_os_str().to_string_lossy()); | |
a.push("ucd.all.flat.xml"); | |
println!("{}", a.as_os_str().to_string_lossy()); | |
let contents = fs::read_to_string(a) | |
.expect("File read error"); | |
let root: Element = contents.parse().unwrap(); | |
let mut data: [u8; 139264] = [0; 139264]; | |
for child in root.children() { | |
if child.name().eq("repertoire") { | |
for subchild in child.children() { | |
if !subchild.attr("cp").is_none() { | |
if subchild.attr("Upper").unwrap() == "Y" { | |
let z = | |
i64::from_str_radix(subchild.attr("cp").unwrap(), 16) | |
.expect("An error occured while decoding hex number"); | |
let index = z >> 3; | |
let ae = z - (index << 3); | |
data[index as usize] += 1 << ae; | |
println!("{} {} {} {}", z, index, ae, data[index as usize]) | |
} | |
} | |
} | |
} | |
} | |
let mut pos = 0; | |
let mut buffer = File::create("out.bin").expect("Failed to create file"); | |
while pos < data.len() { | |
let bytes_written = buffer.write(&data[pos..]) | |
.expect("Failed to write data"); | |
pos += bytes_written; | |
} | |
buffer.flush().expect("Failed to flush the file down the toilet"); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment