feat: add utf8 fix

packages/library/src/utils/utf8.ts

@@ -0,0 +1,131 @@
+"use strict";
+
+/**
+ * Object containing Latin-1 characters and their corresponding UTF-8 characters.
+ * Key is the actual character, value is the expected character.
+ */
+const replacements: Record<string, string> = {
+  "€": "€",
+  "Å’": "Œ",
+  "Ž": "Ž",
+  "“": "“",
+  "â€\u009D": "”",
+  "•": "•",
+  "–": "–",
+  "—": "—",
+  Ëœ: "˜",
+  "â„¢": "™",
+  "Å¡": "š",
+  "›": "›",
+  "Å“": "œ",
+  "ž": "ž",
+  "Ÿ": "Ÿ",
+  "Â ": " ",
+  "¡": "¡",
+  "¢": "¢",
+  "£": "£",
+  "¤": "¤",
+  "Â¥": "¥",
+  "¦": "¦",
+  "§": "§",
+  "¨": "¨",
+  "©": "©",
+  "­": "­",
+  "®": "®",
+  "¯": "¯",
+  "°": "°",
+  "±": "±",
+  "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",
+  "½": "œ"
+};
+
+// Cache immutable regex as they are expensive to create and garbage collect.
+const matchRegex = 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}
+ * @see {@link https://github.com/Fdawgs/fix-latin1-to-utf8/blob/main/src/index.js | Original source}
+ */
+function fixLatin1ToUtf8 (str: string): string {
+  return str.replace(matchRegex, (match) => replacements[match]).normalize();
+}
+
+export default fixLatin1ToUtf8;