Unicode & Internationalization in JavaScript

// Unicode flag and properties
/\p{Emoji}/u.test('😀')           // true
/\p{Letter}/u.test('א')           // true (Hebrew letter)
/\p{Script=Greek}/u.test('Ω')     // true
/\p{Currency_Symbol}/u.test('€')  // true

// Unicode categories
\p{L}   Letter
\p{N}   Number
\p{P}   Punctuation
\p{S}   Symbol
\p{Z}   Separator

// Match any letter (including non-ASCII)
"Hello世界".match(/\p{L}+/u)      // Matches letters from any language

// Match specific scripts
/\p{Script=Han}+/u                // Chinese characters
/\p{Script=Arabic}+/u              // Arabic script
/\p{Script=Cyrillic}+/u            // Cyrillic script

// Emoji handling
const emojiRegex = /\p{Emoji_Presentation}|\p{Emoji}️/gu
"Hello 👋 World 🌍!".match(emojiRegex)  // ['👋', '🌍']

// Remove diacritics (accents)
const text = "café naïve résumé"
text.normalize("NFD").replace(/\p{Diacritic}/gu, "")
// "cafe naive resume"

// Match words in any language
/\p{L}+/gu.exec("Hello世界مرحبا")
// Matches: "Hello", "世界", "مرحبا"

// Case-insensitive Unicode
/\u{00E9}/ui.test('\u{00C9}')    // true (é matches É)