const regex = new RegExp('(?:<!\\[CDATA\\[(?<cdata>.*?)\\]\\]>|(?<xml><\\?.*?\\?>)|<!--(?<comment>.*?)-->|<\\s*(?<tag>[A-z][A-z0-9-_.:]*)(?:\\s+(?:[A-z][A-z0-9-_.:]*)\\s*(?:=\\s*(?<quote>["\\'])((?:\\\\\\k<quote>|(?:(?!\\k<quote>)).)*)(\\k<quote>)\\s*)?)*\\s*(?:/\\s*>|>(?<innerHTML>.*)?<\\s*/\\s*\\k<tag>\\s*>)|(?<text>[^<]*))', 'gms')
const str = `<?xml version='1.0' encoding='shift_jis'?>
<!-- foo -->
<foo>bar</foo>
Baz
<foo asdf="foo" />
<CharacterInfo defaultUid=''>
<Character
name='??????'
uid='511111'
weapon='??'
HR='7' GR='0' lastLogin='1645561498'
sex='M' />
<Character name ='Potatoe/>sss' uid= '511111' weapon = '??' HR='7' GR="0" lastLogin='1645561498' sex='M' />
</CharacterInfo>
Plain text
<hr/>
Multi
line
text
<br />
<!--
This is a comment!
<foo />
-->
<foo
bar/>
<baz asdf="2"></baz>
<asd foo="asd\\"q'we" / >
<b>Hello, <i>World</i>!</b>
<Character
name='??????'
uid='511111'
weapon='??'
HR='7' GR='0' lastLogin='1645561498'
sex='M' />
<Character name ='Potatoe/>sss' uid= '511111' weapon = '??' HR='7' GR="0" lastLogin='1645561498' sex='M' />
<![CDATA[]]>
<![CDATA[Foobar<>]]>
<![CDATA[
asdasdasd
adsd
sd
sd
]]>
`;
// 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