A tiny package that removes common unicode confusables/homoglyphs from strings.
Rust (v1.64 or later)
In your Cargo.toml
:
decancer = "2.0.1"
JavaScript (Node.js)
In your shell:
$ npm install decancer
In your code (CommonJS):
const decancer = require('decancer')
In your code (ESM):
import decancer from 'decancer'
JavaScript (Browser)
In your code:
<script type="module">
import init from 'https://cdn.jsdelivr.net/gh/null8626/decancer@v2.0.1/bindings/wasm/bin/decancer.min.js'
const decancer = await init()
</script>
C/C++
Prerequisites:
$ git clone https://github.com/null8626/decancer.git --depth 1
$ cd decancer/bindings/native
$ cargo build --release
And the binary files should be generated in the target/release
directory.
Rust
For more information, please read the documentation.
let cured = decancer::cure("vοΌ₯β‘π π½πΕβο½ Ε£δΉππ£").unwrap();
assert_eq!(cured, "very funny text");
assert!(cured.contains("FuNny"));
assert_eq!(cured.into_str(), String::from("very funny text"));
JavaScript (Node.js)
const assert = require('node:assert')
const cured = decancer('vοΌ₯β‘π π½πΕβο½ Ε£δΉππ£')
assert(cured.equals('very funny text'))
assert(cured.contains('funny'))
console.log(cured.toString())
// => 'very funny text'
JavaScript (Browser)
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<title>Decancerer!!! (tm)</title>
<style>
textarea {
font-size: 30px;
}
#cure {
font-size: 20px;
padding: 5px 30px;
}
</style>
</head>
<body>
<h3>Input cancerous text here:</h3>
<textarea rows="10" cols="30"></textarea>
<br />
<button id="cure" onclick="cure()">cure!</button>
<script type="module">
import init from 'https://cdn.jsdelivr.net/gh/null8626/decancer@v2.0.1/bindings/wasm/bin/decancer.min.js'
const decancer = await init()
window.cure = function () {
const textarea = document.querySelector('textarea')
if (!textarea.value.length) {
return alert("There's no text!!!")
}
textarea.value = decancer(textarea.value).toString()
}
</script>
</body>
</html>
C/C++
#include <decancer.h>
#include <string.h>
#include <stdlib.h>
#include <stdio.h>
// global variable for assertion purposes only
decancer_cured_t cured;
static void assert(const bool expr, const char *message)
{
if (!expr)
{
fprintf(stderr, "assertion failed (%s)\n", message);
decancer_free(cured);
exit(1);
}
}
static void print_error(decancer_error_t error_code)
{
char message[90];
uint8_t message_size;
const uint8_t *ptr = decancer_error(error_code, &message_size);
memcpy(message, ptr, message_size);
// rust strings are NOT null-terminated
message[message_size] = '\0';
fprintf(stderr, "error: %s", message);
}
int main(void) {
decancer_error_t error_code;
// utf-8 bytes for "vοΌ₯β‘π π½πΕβο½ Ε£δΉππ£"
uint8_t string[] = {0x76, 0xef, 0xbc, 0xa5, 0xe2, 0x93, 0xa1, 0xf0, 0x9d, 0x94, 0x82, 0x20, 0xf0, 0x9d,
0x94, 0xbd, 0xf0, 0x9d, 0x95, 0x8c, 0xc5, 0x87, 0xe2, 0x84, 0x95, 0xef, 0xbd, 0x99,
0x20, 0xc5, 0xa3, 0xe4, 0xb9, 0x87, 0xf0, 0x9d, 0x95, 0x8f, 0xf0, 0x9d, 0x93, 0xa3};
cured = decancer_cure(string, sizeof(string), &error_code);
if (cured == NULL)
{
print_error(error_code);
return 1;
}
assert(decancer_equals(cured, (uint8_t *)("very funny text"), 15), "equals");
assert(decancer_contains(cured, (uint8_t *)("funny"), 5), "contains");
// coerce output as a raw UTF-8 pointer and retrieve its size (in bytes)
size_t output_size;
const uint8_t *output_raw = decancer_raw(cured, &output_size);
assert(output_size == 15, "raw output size");
// utf-8 bytes for "very funny text"
const uint8_t expected_raw[] = {0x76, 0x65, 0x72, 0x79, 0x20, 0x66, 0x75, 0x6e,
0x6e, 0x79, 0x20, 0x74, 0x65, 0x78, 0x74};
char assert_message[38];
for (uint32_t i = 0; i < sizeof(expected_raw); i++)
{
sprintf(assert_message, "mismatched utf-8 contents at index %u", i);
assert(output_raw[i] == expected_raw[i], assert_message);
}
decancer_free(cured);
return 0;
}
Please read CONTRIBUTING.md
for newbie contributors who want to contribute!
Author: null8626
Source: https://github.com/null8626/decancer
License: MIT license