Created
December 11, 2014 00:14
-
-
Save abhibeckert/b12e19a85c4806296c7e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Option 1: | |
let urlRegex = "(?i)\\b((?:[a-z][\\w-]+:(?:/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}/)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))+(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’]))" | |
Option 2: | |
let urlRegex = """ | |
(?xi) | |
\b | |
( # Capture 1: entire matched URL | |
(?: | |
[a-z][\w-]+: # URL protocol and colon | |
(?: | |
/{1,3} # 1-3 slashes | |
| # or | |
[a-z0-9%] # Single letter or digit or '%' | |
# (Trying not to match e.g. "URI::Escape") | |
) | |
| # or | |
www\d{0,3}[.] # "www.", "www1.", "www2." … "www999." | |
| # or | |
[a-z0-9.\-]+[.][a-z]{2,4}/ # looks like domain name followed by a slash | |
) | |
(?: # One or more: | |
[^\s()<>]+ # Run of non-space, non-()<> | |
| # or | |
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels | |
)+ | |
(?: # End with: | |
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels | |
| # or | |
[^\s`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars | |
) | |
) | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment