fix-latin1-to-utf8/src/index.js

Fix mojibake when converting Latin-1 encoded text to UTF-8

"use strict";

/**
 * @description Latin-1 characters and their corresponding UTF-8 characters.
 * @type {Readonly<Record<string, string>>}
 */
const REPLACEMENTS = Object.freeze({
	// Actual: Expected
	"€": "€",
	"‚": "‚",
	"Æ’": "ƒ",
	"„": "„",
	"…": "…",
	"â€\u00A0": "†",
	"‡": "‡",
	"ˆ": "ˆ",
	"‰": "‰",
	"Å\u00A0": "Š",
	"‹": "‹",
	"Å’": "Œ",
	"Ž": "Ž",
	"‘": "‘",
	"’": "’",
	"“": "“",
	"â€\u009D": "”",
	"•": "•",
	"–": "–",
	"—": "—",
	Ëœ: "˜",
	"â„¢": "™",
	"Å¡": "š",
	"›": "›",
	"Å“": "œ",
	"ž": "ž",
	"Ÿ": "Ÿ",
	"Â ": " ",
	"¡": "¡",
	"¢": "¢",
	"£": "£",
	"¤": "¤",
	"Â¥": "¥",
	"¦": "¦",
	"§": "§",
	"¨": "¨",
	"©": "©",
	ª: "ª",
	"«": "«",
	"¬": "¬",
	"­": "­",
	"®": "®",
	"¯": "¯",
	"°": "°",
	"±": "±",
	"²": "²",
	"³": "³",
	"´": "´",
	µ: "µ",
	"¶": "¶",
	"·": "·",
	"¸": "¸",
	"¹": "¹",
	º: "º",
	"»": "»",
	"¼": "¼",
	"½": "½",
	"¾": "¾",
	"¿": "¿",
	"À": "À",
	"Â": "Â",
	Ã: "Ã",
	"Ä": "Ä",
	"Ã…": "Å",
	"Æ": "Æ",
	"Ç": "Ç",
	È: "È",
	"É": "É",
	Ê: "Ê",
	"Ë": "Ë",
	ÃŒ: "Ì",
	"Ã\u008D": "Í",
	ÃŽ: "Î",
	"Ã\u008F": "Ï",
	"Ã\u0090": "Ð",
	"Ñ": "Ñ",
	"Ã’": "Ò",
	"Ó": "Ó",
	"Ô": "Ô",
	"Õ": "Õ",
	"Ö": "Ö",
	"×": "×",
	"Ø": "Ø",
	"Ù": "Ù",
	Ú: "Ú",
	"Û": "Û",
	Ãœ: "Ü",
	"Ã\u009D": "Ý",
	Þ: "Þ",
	ß: "ß",
	"Ã\u00A0": "à",
	"á": "á",
	"â": "â",
	"ã": "ã",
	"ä": "ä",
	"Ã¥": "å",
	"æ": "æ",
	"ç": "ç",
	"è": "è",
	"é": "é",
	ê: "ê",
	"ë": "ë",
	"ì": "ì",
	"Ã\u00AD": "í",
	"î": "î",
	"ï": "ï",
	"ð": "ð",
	"ñ": "ñ",
	"ò": "ò",
	"ó": "ó",
	"ô": "ô",
	õ: "õ",
	"ö": "ö",
	"÷": "÷",
	"ø": "ø",
	"ù": "ù",
	ú: "ú",
	"û": "û",
	"ü": "ü",
	"ý": "ý",
	"þ": "þ",
	"ÿ": "ÿ",
});

// Cache immutable regex as they are expensive to create and garbage collect
const LATIN1_PATTERN = /[ãâåæë]/iu;
// eslint-disable-next-line security/detect-non-literal-regexp -- Static regex, no user input
const MATCH_REG = new RegExp(Object.keys(REPLACEMENTS).join("|"), "gu");

/**
 * @author Frazer Smith
 * @description Fixes common encoding errors when converting from Latin-1 (and Windows-1252) to UTF-8.
 * @see {@link http://www.i18nqa.com/debug/utf8-debug.html | UTF-8 Encoding Debugging Chart}
 * @param {string} str - The string to be converted.
 * @returns {string} The converted string.
 * @throws {TypeError} If the argument is not a string.
 */
function fixLatin1ToUtf8(str) {
	if (typeof str !== "string") {
		throw new TypeError("Expected a string");
	}

	// Early return if no matches
	if (!LATIN1_PATTERN.test(str)) {
		return str;
	}

	return str.replace(MATCH_REG, (match) => REPLACEMENTS[match]);
}

module.exports = fixLatin1ToUtf8; // CommonJS export
module.exports.default = fixLatin1ToUtf8; // ESM default export
module.exports.fixLatin1ToUtf8 = fixLatin1ToUtf8; // TypeScript and named export
module.exports.REPLACEMENTS = REPLACEMENTS;