const regex = /(?<![\p{L}\p{N}_])gen/gmu;
// Alternative syntax using RegExp constructor
// const regex = new RegExp('(?<![\\p{L}\\p{N}_])gen', 'gmu')
const str = `To achieve this, I am using the regular expression /\\bsea/gmi, which works perfectly with English characters. However, it fails to produce the desired results when applied to Swedish characters, like 'ä', 'å', and 'ö'. For example, if the search word is 'gen', the postfix 'gen' in the word 'vägen' is incorrectly highlighted. It seems that the regular expression treats these characters as special characters or something similar. I even tried adding unicode modifier u but that didt't help either.
gen
gena
agen
ägen
genä
`;
// Reset `lastIndex` if this regex is defined globally
// regex.lastIndex = 0;
let m;
while ((m = regex.exec(str)) !== null) {
// This is necessary to avoid infinite loops with zero-width matches
if (m.index === regex.lastIndex) {
regex.lastIndex++;
}
// The result can be accessed through the `m`-variable.
m.forEach((match, groupIndex) => {
console.log(`Found match, group ${groupIndex}: ${match}`);
});
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for JavaScript, please visit: https://developer.mozilla.org/en/docs/Web/JavaScript/Guide/Regular_Expressions