| function( | |
| a, // XHTML input string | |
| b, // result placeholder (starts as undefined, turns true on error) | |
| c // Node stack | |
| ){ | |
| // initialize nodeName stack as array | |
| c=[]; | |
| // search all tags withtin the strings and interpret them within a callback | |
| a.replace(/<(\/?)(\w+).*?(\/?)>/g, function( | |
| d, // full matched string (unused) | |
| e, // closing tag? "/" vs. "" | |
| f, // node name | |
| g // self-closing tag? "/" vs. "" | |
| ){ | |
| // is it a closing tag? | |
| e ? | |
| // b is true (and stays true) if the last node name on the stack is unequal to the current one | |
| b = b || c.pop() != f : | |
| // check if self-closing tag, otherwise add current node name to stack | |
| g || c.push(f) | |
| }); | |
| // result is if no node name mismatch and nothing left on the stack | |
| return !b && !c[0] | |
| } |
| function(a,b,c){c=[];a.replace(/<(\/?)(\w+).*?(\/?)>/g,function(d,e,f,g){e?b=b||c.pop()!=f:g||c.push(f)});return!b&&!c[0]} |
| DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE | |
| Version 2, December 2004 | |
| Copyright (C) 2011 Alex Kloss <alexthkloss@web.de> | |
| Everyone is permitted to copy and distribute verbatim or modified | |
| copies of this license document, and changing it is allowed as long | |
| as the name is changed. | |
| DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE | |
| TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION | |
| 0. You just DO WHAT THE FUCK YOU WANT TO. |
| { | |
| "name": "checkMarkup", | |
| "description": "checks if all opened nodes within a string are closed correctly for XHTML-Style markup", | |
| "keywords": [ | |
| "XHTML", | |
| "markup", | |
| "validation", | |
| "string" | |
| ] | |
| } |
| <!DOCTYPE html> | |
| <title>checkMarkup</title> | |
| <div>Expected value: <b>true,false,false</b></div> | |
| <div>Actual value: <b id="ret"></b></div> | |
| <script> | |
| var myFunction = function(a,b,c){c=[];a.replace(/<(\/?)(\w+).*?(\/?)>/g,function(d,e,f,g){e?b=b||c.pop()!=f:g||c.push(f)});return!b&&!c[0]} | |
| document.getElementById( "ret" ).innerHTML = [ | |
| myFunction('<div id="nav"><ul><li class="first"><a href="#1"><img/></a></li><li class="last"><a href="#2"><img/></a></li></ul></div>'), | |
| myFunction('<p>this is invalid XHTML<p>because the closing tags are missing'), | |
| myFunction('<p>Does not work on HTML-style single-tags (due to size limit): <img></p>') | |
| ]; | |
| </script> |
That is true, but it would fail on attributes within the tags. This example has a practical purpose: to check 3rd-party code before inserting into our pages...
Ah ok, I didn't see any attributes in the examples so I thought this would be constrained to attribute-less markup.
Added some attributes to the example in order to make this more clear.
Skimmed another 2 bytes off by exchanging !g&& with g|| and removed unnecessary ;... we're now down to 123 bytes
\w contains numbers and underlines(_), and i don't think non-alphabet characters are valid for tag names...
Maybe [a-z] instead?
[a-zA-Z:] would be more like it, so it could feature XML namespaces, too
Good idea.
Also, it seems the colon should follow some rules when using XML namespaces.
By the way, should something like <p>some texts</P> pass the checking?
Nope, because not valid XHTML - the closing tag should have the same case as the opening tag
This should take care of the tag names (138bytes):
function(a,b,c){return b=c=[],a.replace(/<(\/?)([a-zA-Z][a-zA-Z:]+).*?(\/?)>/g,function(d,e,f,g){e?b+=c.pop()!=f:g||c.push(f)}),!b&&!c[0]}...not enough place for .toLowerCase(), anyway.
/<(/?)([a-z][a-z:]+).*?(/?)>/gi
...shaving off another 5 bytes. Nice one :)
switch up the declaration for 1 more byte:
function(a,b,c){c=[];a.replace(/<(\/?)(\w+).*?(\/?)>/g,function(d,e,f,g){e?b=b||c.pop()!=f:g||c.push(f)});return!b&&!c[0]}
Even for well-formed XML we should first filter input string with something like
s.replace(/<!(\[CDATA\[[\s\S]*?\]\]|--[\s\S]*?--|[\s\S]*?)>|<\?[\s\S]*?\?>/g,0)in order to strip CDATA sections, PI's, doctypes and comments.
And... Parsing (X)HTML with regex isn't a good idea, you know.
I lol'd. The next answer seems quite sensible and quite matching the current case, though.
One byte less: /<(/?)(\w+)\b(/?)>/g
Also, in most regex engines \b is faster than .*?