Skip to content

Instantly share code, notes, and snippets.

@westc
Last active February 13, 2022 22:50
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save westc/dc1b74018d278147e05cac3018acd8e5 to your computer and use it in GitHub Desktop.
Save westc/dc1b74018d278147e05cac3018acd8e5 to your computer and use it in GitHub Desktop.
A tag function which makes it possible to create verbose regular expressions in JavaScript. A verbose regular expression is one which ignores the whitespace unless it is escaped with a leading backslash.
/**
* A tag function which can be used to create verbose regular expressions.
* @license Copyright 2021 - Chris West - MIT Licensed
* @see https://gist.github.com/westc/dc1b74018d278147e05cac3018acd8e5
*/
function vRegExp(input, ...fillins) {
let {raw} = input;
let content = raw[0];
for (let i = 1, l = raw.length; i < l; i++) {
content += fillins[i - 1] + raw[i];
}
content = content
// Escapes whitespaces within character classes.
.replace(
/(^|[^\\])\[([^\\]+|\\.)\]/g,
(_, m1, mX) => (m1 + '[' + mX.replace(/\s/g, '\\$&') + ']')
)
// Removes whitespaces and JS-style comments.
.replace(/(\\[^])|\s+|\/\/.*|\/\*[^]*?\*\//g, '$1');
return new RegExp(
// Removes the leading flags (eg. "(?i)").
content.replace(/^(?:\s*\(\?\w+\))+/g, ''),
// Only keeps the leading flags (eg. "(?i)" becomes "i").
content.replace(/\(\?(\w+)\)|[^(]+|\(/g, '$1')
);
}
// HIDE \\
console.load('local://vRegExp.js');
// \\
// Regular expression used by srt2vtt to parse subtitles.
var lineBreak = String.raw`(?:\r?\n|\r)`;
var RGX_SRT = vRegExp`
(?gm) // Global and multiline
^\d+$ // Subtitle number indicator
${lineBreak} // Line break
^(?<time1a>[\d:]+)[\.,](?<time1b>\d+) // Line starting with time range
\s*-->\s* // Time range separator
(?<time2a>[\d:]+)[\.,](?<time2b>\d+)$ // Line ending with time range
${lineBreak} // Line break
(?<text>(?:^[^\r\n]+$\r?\n)+) // One or more lines of text
${lineBreak} // Line break
`;
console.log(RGX_SRT);
// \\
var srtCode = `
1
00:00:00,000 --> 00:00:01,053
Hello crazy
world!
1
00:00:01,054 --> 00:00:02,987
This is a good test.
`;
console.log(RGX_SRT.exec(srtCode));
function runIOApp(strRegExp) {
return vRegExp`${strRegExp}`.toString();
}
{
// Where the JS code lies
"files": ["vRegExp.js", "~io-app.js"],
// Name of the function responsable for transforming the input into the output.
"transform": "runIOApp",
// Input setup
"input": {
"language": "text",
"label": "Input - Verbose Regular Expression",
"value": "(?i) // Ignore casing just because we can ;)\n^([a-z0-9_\\.-]+) // local Part\n@ // single @ sign\n([0-9a-z\\.-]+) // Domain name\n\\. // single Dot\n([a-z]{2,6})$ // Top level Domain"
},
// Output setup
"output": { "language": "javascript", "label": "Output - JavaScript Regular Expression" },
// Type of YourJS IO-App
"type": "split",
// title
"title": "Verbose Regular Expressions in JavaScript",
// description
"description": "Use the custom vRegExp tag function which turns a template string into a regular expression while simulating a verbose regular expression."
}
@westc
Copy link
Author

westc commented Nov 17, 2021

@westc
Copy link
Author

westc commented Feb 13, 2022

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment