# ansi-regex

> Regular expression for matching [ANSI escape codes](https://en.wikipedia.org/wiki/ANSI_escape_code)

## Install

```sh
npm install ansi-regex
```

## Usage

```js
import ansiRegex from 'ansi-regex';

ansiRegex().test('\u001B[4mcake\u001B[0m');
//=> true

ansiRegex().test('cake');
//=> false

'\u001B[4mcake\u001B[0m'.match(ansiRegex());
//=> ['\u001B[4m', '\u001B[0m']

'\u001B[4mcake\u001B[0m'.match(ansiRegex({onlyFirst: true}));
//=> ['\u001B[4m']

'\u001B]8;;https://github.com\u0007click\u001B]8;;\u0007'.match(ansiRegex());
//=> ['\u001B]8;;https://github.com\u0007', '\u001B]8;;\u0007']
```

## API

### ansiRegex(options?)

Returns a regex for matching ANSI escape codes.

#### options

Type: `object`

##### onlyFirst

Type: `boolean`\
Default: `false` *(Matches any ANSI escape codes in a string)*

Match only the first ANSI escape.

## Important

If you run the regex against untrusted user input in a server context, you should [give it a timeout](https://github.com/sindresorhus/super-regex).

**I do not consider [ReDoS](https://blog.yossarian.net/2022/12/28/ReDoS-vulnerabilities-and-misaligned-incentives) a valid vulnerability for this package.**

## FAQ

### Which sequences are supported?

The regex matches complete CSI sequences, OSC strings, ST-terminated DCS/SOS/PM/APC strings, screen window-title strings, character-set and encoding selections, and common two-byte ESC controls. Both seven-bit escape sequences and their C1 equivalents are supported where applicable. Linux console palette controls are also supported.

Control-string payloads are opaque, so this includes terminal hyperlinks, shell integration, clipboard commands, editor queries, sixel images, and Kitty graphics without needing a list of individual commands. ESC, CAN, SUB, and C1 control characters delimit or interrupt a control string.

This is a matcher for contiguous terminal output sequences, not a terminal emulator. It does not reconstruct screen contents, decode terminal keyboard/mouse input, or handle nested escape payloads such as tmux passthrough. Incomplete or cancelled sequences are handled on a best-effort basis. Standalone control characters, including tabs, newlines, and BEL, are preserved.

### Why do you test for codes not in the ECMA 48 standard?

Some of the codes we run as a test are codes that we acquired finding various lists of non-standard or manufacturer specific codes. We test for both standard and non-standard codes, as most of them follow the same or similar format and can be safely matched in strings without the risk of removing actual string content. There are a few non-standard control codes that do not follow the traditional format (i.e. they end in numbers) thus forcing us to exclude them from the test because we cannot reliably match them.

On the historical side, those ECMA standards were established in the early 90's whereas the VT100, for example, was designed in the mid/late 70's. At that point in time, control codes were still pretty ungoverned and engineers used them for a multitude of things, namely to activate hardware ports that may have been proprietary. Somewhere else you see a similar 'anarchy' of codes is in the x86 architecture for processors; there are a ton of "interrupts" that can mean different things on certain brands of processors, most of which have been phased out.

## Maintainers

- [Sindre Sorhus](https://github.com/sindresorhus)
- [Josh Junon](https://github.com/qix-)