urlamafication

gistfile1.php

<?php
  $text = "Whatever stuff with URLs in it.";

  $protocols = array('http', 'https', 'ftp');
  $protocols = implode(':(?://)?|', $protocols) . ':(?://)?';

  // Prepare domain name pattern.
  // The ICANN seems to be on track towards accepting more diverse top level
  // domains, so this pattern has been "future-proofed" to allow for TLDs
  // of length 2-64.
  $domain = '(?:[A-Za-z0-9._+-]+\.)?[A-Za-z]{2,64}\b';
  $ip = '(?:[0-9]{1,3}\.){3}[0-9]{1,3}';
  $auth = '[a-zA-Z0-9:%_+*~#?&=.,/;-]+@';
  $trail = '[a-zA-Z0-9:%_+*~#&\[\]=/;?!\.,-]*[a-zA-Z0-9:%_+*~#&\[\]=/;-]';

  // Prepare pattern for optional trailing punctuation.
  // Even these characters could have a valid meaning for the URL, such usage is
  // rare compared to using a URL at the end of or within a sentence, so these
  // trailing characters are optionally excluded.
  $punctuation = '[\.,?!]*?';

  // Match absolute URLs.
  $url_pattern = "(?:$auth)?(?:$domain|$ip)/?(?:$trail)?";
  $pattern = "`((?:$protocols)(?:$url_pattern))($punctuation)`";

  $count = preg_match_all($pattern, $text, $matches);

  $replace = array();

  // Grab the relative node link, and rewrite it to the alias. Then
  // add it to the array of replacements to perform.
  for($i = 0; $i < $count; $i++) {
    $replace[$matches[0][$i]] = '[URL=' . $matches[0][$i] . ']' . basename($matches[0][$i]) . '[/URL]';
  }

  // Replace the links in the text, return it.
  return strtr($text, $replace);