🚩flag /u

JS ⟩ value ⟩ object ⟩ regex ⟩ flag ⟩ /u

// support unicode 
/abc/u       // treated as sequence of code points.

// ❗️'/u' flag doesn't do well with grapheme clusters.
/<.>/u.test("<🏳️‍🌈>")                          // false❗️
/<....>/u.test("<🏳️‍🌈>")                       // true ⭐️

👉 code point, grapheme cluster

🧨 雷區

'/u' flag doesn't do well with grapheme clusters❗

// ❗️'/u' flag doesn't do well with grapheme clusters.
/<.>/u.test("<🏳️‍🌈>"),                          // false❗️
/<....>/u.test("<🏳️‍🌈>"),                       // true ⭐️

⭐️ 重點

flag /u works on code points, not on grapheme clusters❗

💈範例

• replit ⟩ /u flag, require ⟩ String extension

// ⭐ import
const _String = require('./ext/String_ext.js');      // String extension

[
    '🍎'.codeUnits,     // [ 55356, 57166 ]     // surrogate pair (2 code units)
    '🍎'.codePoints,    // [ 127822 ]           // 1 code point

    '🏳️‍🌈'.codeUnits,     // [ 55356, 57331, 65039, 8205, 55356, 57096 ]
    '🏳️‍🌈'.codePoints,    // [ 127987, 65039, 8205, 127752 ]    // 4 code points❗️

    // --------------------------------------------
    // ❗️regex works on "code units", by default.
    // --------------------------------------------
    
    /🍎{3}/.test("🍎🍎🍎"),                      // false❗️
    // let 🍎 = ab (where a = 55356, b = 57166)
    // then /🍎{3}/ = /ab{3}/ = /abbb/❗️
    // which is not /🍎🍎🍎/ = /ababab/❗️

    /<.>/.test("<🍎>"),                           // false❗️
    // <🍎> = <ab>, which is not <.>

    // --------------------
    // ✅ enable /u flag
    // --------------------

    /<.>/u.test("<🍎>"),                          // true ⭐️

    // ❗️'/u' flag doesn't do well with grapheme clusters.
    /<.>/u.test("<🏳️‍🌈>"),                          // false❗️
    /<....>/u.test("<🏳️‍🌈>"),                       // true ⭐️

    // ⭐️ 搜尋「漢字」
    `Hello Привет 你好`.match(/\p{sc=Han}/gu),     // [ '你', '好' ]

    // ⭐️ Script
    /\p{Script=Greek}/u.test("α"),      // → true
    /\p{Script=Arabic}/u.test("α"),     // → false

    // ⭐️ Alphabetic
    /\p{Alphabetic}/u.test("α"),        // → true
    /\p{Alphabetic}/u.test("!"),        // → false
    /\p{Alphabetic}/u.test("漢"),       // → true

].forEach(x => console.log(x));

📗 參考

• Eloquent JS ⟩ Regular Expressions ⟩ International Characters