https://github.com/nitely/nim-graphemes

Grapheme aware string handling (Unicode tr29)
https://github.com/nitely/nim-graphemes

graphemeclusters nim unicode

Last synced: 29 days ago
JSON representation

Grapheme aware string handling (Unicode tr29)

• Host: GitHub
• URL: https://github.com/nitely/nim-graphemes
• Owner: nitely
• License: mit
• Created: 2017-09-05T05:41:58.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2024-09-19T20:02:41.000Z (5 months ago)
• Last Synced: 2024-11-10T06:42:25.611Z (3 months ago)
• Topics: graphemeclusters, nim, unicode
• Language: Nim
• Homepage: https://nitely.github.io/nim-graphemes/
• Size: 695 KB
• Stars: 11
• Watchers: 4
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# nim-graphemes

[![Build Status](https://img.shields.io/travis/nitely/nim-graphemes.svg?style=flat-square)](https://travis-ci.org/nitely/nim-graphemes)

[![licence](https://img.shields.io/github/license/nitely/nim-graphemes.svg?style=flat-square)](https://raw.githubusercontent.com/nitely/nim-graphemes/master/LICENSE)

A Nim library for grapheme aware string handling (Unicode tr29).

The splitting is made through a fast DFA.

## Install

```

nimble install graphemes

```

## Compatibility

* Nim +1.0.0

## Usage

```nim

import graphemes

# Iterate over graphemes

block:

  let expected = [

    "u̲", "n̲", "d̲", "e̲", "r̲", "l̲", "i̲", "n̲", "e̲", "d̲"]

  var i = 0

  for c in graphemes("u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲"):

    doAssert c == expected[i]

    inc i

assert graphemesCount("u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲") == 10

assert graphemesCount("ю́") == 1

assert graphemesCount("👨‍👩‍👧‍👦") == 1  # Family of 4 emoji

# Get number of bytes the grapheme at index 0 takes

assert graphemeLenAt("u̲n̲d̲e̲r̲", 0) == 3

assert graphemeLenAt("ю́", 0) == 4

# Reverse graphemes

block:

  var s = "🇦🇷🇺🇾🇨🇱"

  s.graphemesReverse

  assert s == "🇨🇱🇺🇾🇦🇷"

# Remove last grapheme

block:

  var s = "u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲"

  s.setLen(s.len - s.graphemeLenAt(^1))

  assert s == "u̲n̲d̲e̲r̲l̲i̲n̲e̲"

# Get sub-string

block:

  # This string contains the following emoji:

  # "flag, family, yawn, vampire, pinch, and diving mask"

  const s = "🇦🇷👨‍👩‍👧‍👦🥱🧛🏻‍♂️🤏🤿"

  assert s.graphemesSubStr(1, 3) == "👨‍👩‍👧‍👦🥱🧛🏻‍♂️"

# Truncate to a limit of graphemes

block:

  var s = "🇦🇷🇺🇾🇨🇱"

  graphemesTruncate(s, 2)

  assert s == "🇦🇷🇺🇾"

block:

  var s = "u̲n̲d̲e̲r̲l̲i̲n̲e̲d̲"

  graphemesTruncate(s, 8, "...")

  assert s == "u̲n̲d̲e̲r̲..."

# Truncate to a limit of bytes preserving the graphemes

block:

  var s = "🇦🇷🇺🇾🇨🇱"

  graphemesTruncateBytes(s, 20)

  assert s == "🇦🇷🇺🇾"

  assert s.len == 16

```

|  

|  

 -> [docs](https://nitely.github.io/nim-graphemes/)

## Tests

```

$ nimble test

```

## License

MIT