diff options
| author | StefanVukovic99 <stefanvukovic44@gmail.com> | 2024-03-03 05:49:41 +0100 | 
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-03 04:49:41 +0000 | 
| commit | 7f28dc887fcafddeea48fb351328df9c7885266a (patch) | |
| tree | 023224e54209da87d62cb39c402c1f530894aedc | |
| parent | 5ec2344df95da39cda4ad07cfe5181b05fa24830 (diff) | |
add diacritics (#756)
| -rw-r--r-- | ext/js/language/ar/arabic-text-preprocessors.js | 18 | 
1 files changed, 17 insertions, 1 deletions
| diff --git a/ext/js/language/ar/arabic-text-preprocessors.js b/ext/js/language/ar/arabic-text-preprocessors.js index f0118564..7adb39e9 100644 --- a/ext/js/language/ar/arabic-text-preprocessors.js +++ b/ext/js/language/ar/arabic-text-preprocessors.js @@ -17,12 +17,28 @@  import {basicTextPreprocessorOptions} from '../text-preprocessors.js'; +const optionalDiacritics = [ +    '\u0618', // Small Fatha +    '\u0619', // Small Damma +    '\u061A', // Small Kasra +    '\u064B', // Fathatan +    '\u064C', // Dammatan +    '\u064D', // Kasratan +    '\u064E', // Fatha +    '\u064F', // Damma +    '\u0650', // Kasra +    '\u0651', // Shadda +    '\u0652' // Sukun +]; + +const diacriticsRegex = new RegExp(`[${optionalDiacritics.join('')}]`, 'g'); +  /** @type {import('language').TextPreprocessor<boolean>} */  export const removeArabicScriptDiacritics = {      name: 'Remove diacritics',      description: 'وَلَدَ ⬅️ ولد',      options: basicTextPreprocessorOptions,      process: (text, setting) => { -        return setting ? text.replace(/[\u064E-\u0650]/g, '') : text; +        return setting ? text.replace(diacriticsRegex, '') : text;      }  }; |