Unicode 字元類轉義：\p{...}, \P{...}

const sentence = "A ticket to 大阪 costs ¥2000 👌.";

const regexpEmojiPresentation = /\p{Emoji_Presentation}/gu;
console.log(sentence.match(regexpEmojiPresentation));
// Expected output: Array ["👌"]

const regexpNonLatin = /\P{Script_Extensions=Latin}+/gu;
console.log(sentence.match(regexpNonLatin));
// Expected output: Array [" ", " ", " 大阪 ", " ¥2000 👌."]

const regexpCurrencyOrPunctuation = /\p{Sc}|\p{P}/gu;
console.log(sentence.match(regexpCurrencyOrPunctuation));
// Expected output: Array ["¥", "."]

\p{loneProperty}
\P{loneProperty}

\p{property=value}
\P{property=value}

// finding all the letters of a text
const story = "It's the Cheshire Cat: now I shall have somebody to talk to.";

// Most explicit form
story.match(/\p{General_Category=Letter}/gu);

// It is not mandatory to use the property name for General categories
story.match(/\p{Letter}/gu);

// This is equivalent (short alias):
story.match(/\p{L}/gu);

// This is also equivalent (conjunction of all the subcategories using short aliases)
story.match(/\p{Lu}|\p{Ll}|\p{Lt}|\p{Lm}|\p{Lo}/gu);

const mixedCharacters = "aεЛ";

// Using the canonical "long" name of the script
mixedCharacters.match(/\p{Script=Latin}/u); // a

// Using a short alias (ISO 15924 code) for the script
mixedCharacters.match(/\p{Script=Grek}/u); // ε

// Using the short name sc for the Script property
mixedCharacters.match(/\p{sc=Cyrillic}/u); // Л

// ٢ is the digit 2 in Arabic-Indic notation
// while it is predominantly written within the Arabic script
// it can also be written in the Thaana script

"٢".match(/\p{Script=Thaana}/u);
// null as Thaana is not the predominant script

"٢".match(/\p{Script_Extensions=Thaana}/u);
// ["٢", index: 0, input: "٢", groups: undefined]

// Trying to use ranges to avoid \w limitations:

const nonEnglishText = "Приключения Алисы в Стране чудес";
const regexpBMPWord = /([\u0000-\u0019\u0021-\uFFFF])+/gu;
// BMP goes through U+0000 to U+FFFF but space is U+0020

console.table(nonEnglishText.match(regexpBMPWord));

// Using Unicode property escapes instead
const regexpUPE = /\p{L}+/gu;
console.table(nonEnglishText.match(regexpUPE));

function getPrices(str) {
  // Sc stands for "currency symbol"
  return [...str.matchAll(/\p{Sc}\s*[\d.,]+/gu)].map((match) => match[0]);
}

const str = `California rolls $6.99
Crunchy rolls $8.49
Shrimp tempura $10.99`;
console.log(getPrices(str)); // ["$6.99", "$8.49", "$10.99"]

const str2 = `US store $19.99
Europe store €18.99
Japan store ¥2000`;
console.log(getPrices(str2)); // ["$19.99", "€18.99", "¥2000"]

const flag = "🇺🇳";
console.log(flag.length); // 2
console.log(/\p{RGI_Emoji_Flag_Sequence}/v.exec(flag)); // [ '🇺🇳' ]

/\P{RGI_Emoji_Flag_Sequence}/v; // SyntaxError: Invalid regular expression: Invalid property name