d9k · October 20, 2014 14:47
diff --git a/php_urls_to_hrefs.php b/php_urls_to_hrefs.php
 <html>
 <head>
 <title>Online PHP Script Execution</title>
 </head>
 <body>
 <?php

 $text = "Hi, my name is ... See my site example.com?test=azaza&ololo=ttt";

 /** @see http://stackoverflow.com/a/1188652/1760643 */

 function urlsToAnchors($text){
  $rexProtocol = '(https?://)?';
  $rexDomain   = '((?:[-a-zA-Z0-9]{1,63}\.)+[-a-zA-Z0-9]{2,63}|(?:[0-9]{1,3}\.){3}[0-9]{1,3})';
  $rexPort     = '(:[0-9]{1,5})?';
  $rexPath     = '(/[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]*?)?';
  $rexQuery    = '(\?[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?';
  $rexFragment = '(#[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?';
  
  $validTlds = array_fill_keys(explode(" ", ".aero .asia .biz .cat .com .coop .edu .gov .info .int .jobs .mil .mobi .museum .name .net .org .pro .tel .travel .ac .ad .ae .af .ag .ai .al .am .an .ao .aq .ar .as .at .au .aw .ax .az .ba .bb .bd .be .bf .bg .bh .bi .bj .bm .bn .bo .br .bs .bt .bv .bw .by .bz .ca .cc .cd .cf .cg .ch .ci .ck .cl .cm .cn .co .cr .cu .cv .cx .cy .cz .de .dj .dk .dm .do .dz .ec .ee .eg .er .es .et .eu .fi .fj .fk .fm .fo .fr .ga .gb .gd .ge .gf .gg .gh .gi .gl .gm .gn .gp .gq .gr .gs .gt .gu .gw .gy .hk .hm .hn .hr .ht .hu .id .ie .il .im .in .io .iq .ir .is .it .je .jm .jo .jp .ke .kg .kh .ki .km .kn .kp .kr .kw .ky .kz .la .lb .lc .li .lk .lr .ls .lt .lu .lv .ly .ma .mc .md .me .mg .mh .mk .ml .mm .mn .mo .mp .mq .mr .ms .mt .mu .mv .mw .mx .my .mz .na .nc .ne .nf .ng .ni .nl .no .np .nr .nu .nz .om .pa .pe .pf .pg .ph .pk .pl .pm .pn .pr .ps .pt .pw .py .qa .re .ro .rs .ru .rw .sa .sb .sc .sd .se .sg .sh .si .sj .sk .sl .sm .sn .so .sr .st .su .sv .sy .sz .tc .td .tf .tg .th .tj .tk .tl .tm .tn .to .tp .tr .tt .tv .tw .tz .ua .ug .uk .us .uy .uz .va .vc .ve .vg .vi .vn .vu .wf .ws .ye .yt .yu .za .zm .zw .xn--0zwm56d .xn--11b5bs3a9aj6g .xn--80akhbyknj4f .xn--9t4b11yi5a .xn--deba0ad .xn--g6w251d .xn--hgbk6aj7f53bba .xn--hlcj6aya9esc7a .xn--jxalpdlp .xn--kgbechtv .xn--zckzah .arpa"), true);
  
  $output = '';
  
  $position = 0;
  while (preg_match("{\\b$rexProtocol$rexDomain$rexPort$rexPath$rexQuery$rexFragment(?=[?.!,;:\"]?(\s|$))}", $text, &$match, PREG_OFFSET_CAPTURE, $position))
  {
      list($url, $urlPosition) = $match[0];
  
      // Print the text leading up to the URL.
      print(htmlspecialchars(substr($text, $position, $urlPosition - $position)));
  
      $domain = $match[2][0];
      $port   = $match[3][0];
      $path   = $match[4][0];
  
      // Check if the TLD is valid - or that $domain is an IP address.
      $tld = strtolower(strrchr($domain, '.'));
      if (preg_match('{\.[0-9]{1,3}}', $tld) || isset($validTlds[$tld]))
      {
          // Prepend http:// if no protocol specified
          $completeUrl = $match[1][0] ? $url : "http://$url";
  
          // Print the hyperlink.
          $output .= sprintf('<a href="%s">%s</a>', htmlspecialchars($completeUrl), htmlspecialchars("$domain$port$path"));
     } 
      else
      {
          // Not a valid URL.
          $output .= htmlspecialchars($url);
      }
  
      // Continue text parsing from after the URL.
      $position = $urlPosition + strlen($url);
  }
  
  // Print the remainder of the text.
  $output .= htmlspecialchars(substr($text, $position));
 }

 function carriageReturnsToBreakTags($text){
  preg_replace('/\r\n?/', "<br>\n", $text);
 } 

 echo carriageReturnsToBreakTags(urlsToAnchors($text));

 ?>
 </body>
 </html>
	<html>
	<head>
	<title>Online PHP Script Execution</title>
	</head>
	<body>
	<?php

	$text = "Hi, my name is ... See my site example.com?test=azaza&ololo=ttt";

	/** @see http://stackoverflow.com/a/1188652/1760643 */

	function urlsToAnchors($text){
	$rexProtocol = '(https?://)?';
	$rexDomain = '((?:[-a-zA-Z0-9]{1,63}\.)+[-a-zA-Z0-9]{2,63}\|(?:[0-9]{1,3}\.){3}[0-9]{1,3})';
	$rexPort = '(:[0-9]{1,5})?';
	$rexPath = '(/[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]*?)?';
	$rexQuery = '(\?[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?';
	$rexFragment = '(#[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?';

	$validTlds = array_fill_keys(explode(" ", ".aero .asia .biz .cat .com .coop .edu .gov .info .int .jobs .mil .mobi .museum .name .net .org .pro .tel .travel .ac .ad .ae .af .ag .ai .al .am .an .ao .aq .ar .as .at .au .aw .ax .az .ba .bb .bd .be .bf .bg .bh .bi .bj .bm .bn .bo .br .bs .bt .bv .bw .by .bz .ca .cc .cd .cf .cg .ch .ci .ck .cl .cm .cn .co .cr .cu .cv .cx .cy .cz .de .dj .dk .dm .do .dz .ec .ee .eg .er .es .et .eu .fi .fj .fk .fm .fo .fr .ga .gb .gd .ge .gf .gg .gh .gi .gl .gm .gn .gp .gq .gr .gs .gt .gu .gw .gy .hk .hm .hn .hr .ht .hu .id .ie .il .im .in .io .iq .ir .is .it .je .jm .jo .jp .ke .kg .kh .ki .km .kn .kp .kr .kw .ky .kz .la .lb .lc .li .lk .lr .ls .lt .lu .lv .ly .ma .mc .md .me .mg .mh .mk .ml .mm .mn .mo .mp .mq .mr .ms .mt .mu .mv .mw .mx .my .mz .na .nc .ne .nf .ng .ni .nl .no .np .nr .nu .nz .om .pa .pe .pf .pg .ph .pk .pl .pm .pn .pr .ps .pt .pw .py .qa .re .ro .rs .ru .rw .sa .sb .sc .sd .se .sg .sh .si .sj .sk .sl .sm .sn .so .sr .st .su .sv .sy .sz .tc .td .tf .tg .th .tj .tk .tl .tm .tn .to .tp .tr .tt .tv .tw .tz .ua .ug .uk .us .uy .uz .va .vc .ve .vg .vi .vn .vu .wf .ws .ye .yt .yu .za .zm .zw .xn--0zwm56d .xn--11b5bs3a9aj6g .xn--80akhbyknj4f .xn--9t4b11yi5a .xn--deba0ad .xn--g6w251d .xn--hgbk6aj7f53bba .xn--hlcj6aya9esc7a .xn--jxalpdlp .xn--kgbechtv .xn--zckzah .arpa"), true);

	$output = '';

	$position = 0;
	while (preg_match("{\\b$rexProtocol$rexDomain$rexPort$rexPath$rexQuery$rexFragment(?=[?.!,;:\"]?(\s\|$))}", $text, &$match, PREG_OFFSET_CAPTURE, $position))
	{
	list($url, $urlPosition) = $match[0];

	// Print the text leading up to the URL.
	print(htmlspecialchars(substr($text, $position, $urlPosition - $position)));

	$domain = $match[2][0];
	$port = $match[3][0];
	$path = $match[4][0];

	// Check if the TLD is valid - or that $domain is an IP address.
	$tld = strtolower(strrchr($domain, '.'));
	if (preg_match('{\.[0-9]{1,3}}', $tld) \|\| isset($validTlds[$tld]))
	{
	// Prepend http:// if no protocol specified
	$completeUrl = $match[1][0] ? $url : "http://$url";

	// Print the hyperlink.
	$output .= sprintf('<a href="%s">%s</a>', htmlspecialchars($completeUrl), htmlspecialchars("$domain$port$path"));
	}
	else
	{
	// Not a valid URL.
	$output .= htmlspecialchars($url);
	}

	// Continue text parsing from after the URL.
	$position = $urlPosition + strlen($url);
	}

	// Print the remainder of the text.
	$output .= htmlspecialchars(substr($text, $position));
	}

	function carriageReturnsToBreakTags($text){
	preg_replace('/\r\n?/', "<br>\n", $text);
	}

	echo carriageReturnsToBreakTags(urlsToAnchors($text));

	?>
	</body>
	</html>