Crate decancer

source ·
Expand description

decancer npm crates.io npm downloads crates.io downloads code style: prettier Build Status license BLAZINGLY FAST!!!

A tiny package that removes common unicode confusables/homoglyphs from strings.

Installation

Rust (v1.64 or later)

In your Cargo.toml:

decancer = "1.6.2"
JavaScript (Node.js v16 or later)

In your shell:

$ npm install decancer

In your code:

const decancer = require('decancer')
JavaScript (Deno v1.28 or later)

In your code:

import decancer from 'npm:decancer'
JavaScript (Bun)

In your shell:

$ bun install decancer

In your code:

const decancer = require('decancer')
JavaScript (Browser)

In your code:

<script type="module">
  import init from 'https://cdn.jsdelivr.net/gh/null8626/decancer@v1.6.2/bindings/wasm/bin/decancer.min.js'

  const decancer = await init()
</script>
C/C++

Download precompiled binaries

Building from source

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.

Examples

note: cured output will always be in lowercase.

Rust 
let cured = decancer::cure("vＥⓡ𝔂 𝔽𝕌Ňℕｙ ţ乇𝕏𝓣");

// cured here is a decancer::CuredString struct wrapping over the cured string
// for comparison purposes, it's more recommended to use the methods provided by the decancer::CuredString struct.

assert_eq!(cured, "very funny text");
assert!(cured.starts_with("very"));
assert!(cured.contains("funny"));
assert!(cured.ends_with("text"));

let _output_str = cured.into_str(); // retrieve the String inside and consume the struct.
JavaScript (Node.js/Deno/Bun) 
const cured = decancer('vＥⓡ𝔂 𝔽𝕌Ňℕｙ ţ乇𝕏𝓣')

// cured here is a CuredString object wrapping over the cured string
// for comparison purposes, it's more recommended to use the methods provided by the CuredString class.

if (cured.contains('funny')) {
  console.log('found the funny')
}

if (
  cured.equals('very funny text') &&
  cured.startsWith('very') &&
  cured.endsWith('text')
) {
  console.log('it works!')
}

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@v1.6.2/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++

note: decancer.h can be retrieved from the bindings/native directory.

#include <decancer.h>

#include <string.h>
#include <stdlib.h>
#include <stdio.h>

// global variable for assertion purposes only
decancer_cured_t cured;

// our quick assert function
static void assert(const bool expr, const char *message)
{
    if (!expr)
    {
        fprintf(stderr, "assertion failed (%s)\n", message);
        decancer_free(cured);
        
        exit(1);
    }
}

int main(void) {
    // utf-8 bytes for "vＥⓡ𝔂 𝔽𝕌Ňℕｙ ţ乇𝕏𝓣"
    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));

    // comparisons
    assert(decancer_equals(cured, (uint8_t *)("very funny text"), 15), "equals");
    assert(decancer_starts_with(cured, (uint8_t *)("very"), 4), "starts_with");
    assert(decancer_ends_with(cured, (uint8_t *)("text"), 4), "ends_with");
    assert(decancer_contains(cured, (uint8_t *)("funny"), 5), "contains");

    // coerce output as a raw UTF-8 pointer and retrieve it's size (in bytes)
    size_t output_size;
    const uint8_t *output_raw = decancer_raw(cured, &output_size);

    // assert raw cured utf-8 size to be 15 bytes (size of "very funny text")
    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);
    }

    // free cured string (required)
    decancer_free(cured);
    
    return 0;
}

Contributing

Please read CONTRIBUTING.md for newbie contributors who want to contribute!

Structs

Enums

  • Translation
    The translation for a single character/codepoint.

Functions