advanced code snippet search

We Recommend

Mastering Regular Expressions Mastering Regular Expressions
As this book shows, a command of regular expressions is an invaluable skill. Regular expressions allow you to code complex and subtle text processing that you never imagined could be automated. Regular expressions can save you time and aggravation. They can be used to craft elegant solutions to a wide range of problems. Once you've mastered regular expressions, they'll become an invaluable part of your toolkit. You will wonder how you ever got by without them.

Posted By

wizard04 on 06/24/08


Tagged

regex email url javascript parse validation uri mailto address


Versions (?)


Who likes this?

1 person has marked this snippet as a favorite

korzhik


Regular Expressions For URI Validation/Parsing

Published in: Regular Expression 

(Supported by JavaScript, maybe other languages)

Plain TextExpand 
  1. //replace() can be used to parse the URI. For example, to get the path:
  2. //  path = uri.replace(regexUri, "$5$6");
  3.  
  4. //****************************************************//
  5. //***************** Validate a URI *******************//
  6. //****************************************************//
  7. //- The different parts are kept in their own groups and can be recombined
  8. //  depending on the scheme:
  9. //  - http as $1://$3:$4$5?$7#$8
  10. //  - ftp as $1://$2@$3:$4$5
  11. //  - mailto as $1:$6?$7
  12. //- groups are as follows:
  13. //  1   == scheme
  14. //  2   == userinfo
  15. //  3   == host
  16. //  4   == port
  17. //  5,6 == path (5 if it has an authority, 6 if it doesn't)
  18. //  7   == query
  19. //  8   == fragment
  20.  
  21. var regexUri = /^([a-z0-9+.-]+):(?://(?:((?:[a-z0-9-._~!$&'()*+,;=:]|%[0-9A-F]{2})*)@)?((?:[a-z0-9-._~!$&'()*+,;=]|%[0-9A-F]{2})*)(?::(\d*))?(/(?:[a-z0-9-._~!$&'()*+,;=:@/]|%[0-9A-F]{2})*)?|(/?(?:[a-z0-9-._~!$&'()*+,;=:@]|%[0-9A-F]{2})+(?:[a-z0-9-._~!$&'()*+,;=:@/]|%[0-9A-F]{2})*)?)(?:\?((?:[a-z0-9-._~!$&'()*+,;=:/?@]|%[0-9A-F]{2})*))?(?:#((?:[a-z0-9-._~!$&'()*+,;=:/?@]|%[0-9A-F]{2})*))?$/i;
  22. /*composed as follows:
  23. 	^
  24. 	([a-z0-9+.-]+):							#scheme
  25. 	(?:
  26. 		//							#it has an authority:
  27. 		(?:((?:[a-z0-9-._~!$&'()*+,;=:]|%[0-9A-F]{2})*)@)?	#userinfo
  28. 		((?:[a-z0-9-._~!$&'()*+,;=]|%[0-9A-F]{2})*)		#host
  29. 		(?::(\d*))?						#port
  30. 		(/(?:[a-z0-9-._~!$&'()*+,;=:@/]|%[0-9A-F]{2})*)?	#path
  31. 		|
  32. 									#it doesn't have an authority:
  33. 		(/?(?:[a-z0-9-._~!$&'()*+,;=:@]|%[0-9A-F]{2})+(?:[a-z0-9-._~!$&'()*+,;=:@/]|%[0-9A-F]{2})*)?	#path
  34. 	)
  35. 	(?:
  36. 		\?((?:[a-z0-9-._~!$&'()*+,;=:/?@]|%[0-9A-F]{2})*)	#query string
  37. 	)?
  38. 	(?:
  39. 		#((?:[a-z0-9-._~!$&'()*+,;=:/?@]|%[0-9A-F]{2})*)	#fragment
  40. 	)?
  41. 	$
  42. */
  43.  
  44. //****************************************************//
  45. //** Validate a URI (includes delimiters in groups) **//
  46. //****************************************************//
  47. //- The different parts--along with their delimiters--are kept in their own
  48. //  groups and can be recombined as $1$6$2$3$4$5$7$8$9
  49. //- groups are as follows:
  50. //  1,6 == scheme:// or scheme:
  51. //  2   == userinfo@
  52. //  3   == host
  53. //  4   == :port
  54. //  5,7 == path (5 if it has an authority, 7 if it doesn't)
  55. //  8   == ?query
  56. //  9   == #fragment
  57.  
  58. var regexUriDelim = /^(?:([a-z0-9+.-]+:\/\/)((?:(?:[a-z0-9-._~!$&'()*+,;=:]|%[0-9A-F]{2})*)@)?((?:[a-z0-9-._~!$&'()*+,;=]|%[0-9A-F]{2})*)(:(?:\d*))?(\/(?:[a-z0-9-._~!$&'()*+,;=:@\/]|%[0-9A-F]{2})*)?|([a-z0-9+.-]+:)(\/?(?:[a-z0-9-._~!$&'()*+,;=:@]|%[0-9A-F]{2})+(?:[a-z0-9-._~!$&'()*+,;=:@\/]|%[0-9A-F]{2})*)?)(\?(?:[a-z0-9-._~!$&'()*+,;=:\/?@]|%[0-9A-F]{2})*)?(#(?:[a-z0-9-._~!$&'()*+,;=:\/?@]|%[0-9A-F]{2})*)?$/i;
  59.  
  60. //****************************************************//
  61. //***************** Validate a URL *******************//
  62. //****************************************************//
  63. //Validates a URI with an http or https scheme.
  64. //- The different parts are kept in their own groups and can be recombined as
  65. //  $1://$2:$3$4?$5#$6
  66. //- Does not validate the host portion (domain); just makes sure the string
  67. //  consists of valid characters (does not include IPv6 nor IPvFuture
  68. //  addresses as valid).
  69.  
  70. var regexUrl = /^(https?):\/\/((?:[a-z0-9.-]|%[0-9A-F]{2}){3,})(?::(\d+))?((?:\/(?:[a-z0-9-._~!$&'()*+,;=:@]|%[0-9A-F]{2})*)*)(?:\?((?:[a-z0-9-._~!$&'()*+,;=:\/?@]|%[0-9A-F]{2})*))?(?:#((?:[a-z0-9-._~!$&'()*+,;=:\/?@]|%[0-9A-F]{2})*))?$/i;
  71.  
  72. //****************************************************//
  73. //**************** Validate a Mailto *****************//
  74. //****************************************************//
  75. //Validates a URI with a mailto scheme.
  76. //- The different parts are kept in their own groups and can be recombined as
  77. //  $1:$2?$3
  78. //- Does not validate the email addresses themselves.
  79.  
  80. var regexMailto = /^(mailto):((?:[a-z0-9-._~!$&'()*+,;=:@]|%[0-9A-F]{2})+)?(?:\?((?:[a-z0-9-._~!$&'()*+,;=:\/?@]|%[0-9A-F]{2})*))?$/i;

Report this snippet 

You need to login to post a comment.