From 9285c8c66c530196399eb05bb5561c3fa5538335 Mon Sep 17 00:00:00 2001
From: Bharat Mediratta <bharat@menalto.com>
Date: Mon, 21 Dec 2009 20:05:27 -0800
Subject: Updated Kohana to r4724

---
 system/helpers/text.php | 46 ++++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 18 deletions(-)

(limited to 'system/helpers/text.php')

diff --git a/system/helpers/text.php b/system/helpers/text.php
index 66bcd243..ed7f9cbf 100644
--- a/system/helpers/text.php
+++ b/system/helpers/text.php
@@ -2,7 +2,7 @@
 /**
  * Text helper class.
  *
- * $Id: text.php 4679 2009-11-10 01:45:52Z isaiah $
+ * $Id: text.php 4689 2009-12-02 01:39:24Z isaiah $
  *
  * @package    Core
  * @author     Kohana Team
@@ -298,27 +298,37 @@ class text_Core {
 	 */
 	public static function auto_link_urls($text)
 	{
-		// Finds all http/https/ftp/ftps links that are not part of an existing html anchor
-		if (preg_match_all('~\b(?<!href="|">)(?:ht|f)tps?://\S+(?:/|\b)~i', $text, $matches))
-		{
-			foreach ($matches[0] as $match)
-			{
-				// Replace each link with an anchor
-				$text = str_replace($match, html::anchor($match), $text);
-			}
-		}
 
-		// Find all naked www.links.com (without http://)
-		if (preg_match_all('~\b(?<!://)www(?:\.[a-z0-9][-a-z0-9]*+)+\.[a-z]{2,6}\b~i', $text, $matches))
+		$regex = '~\\b'
+				.'((?:ht|f)tps?://)?' // protocol
+				.'(?:[-a-zA-Z0-9]{1,63}\.)+' // host name
+				.'(?:[0-9]{1,3}|aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)' // tlds
+				.'(?:/[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]*?)?' // path
+				.'(?:\?[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?' // query
+				.'(?:#[!$-/0-9:;=@_\':;!a-zA-Z\x7f-\xff]+?)?' // fragment
+				.'(?=[?.!,;:"]?(?:\s|$))~'; // punctuation and url end
+
+		$result = "";
+		$position = 0;
+
+		while (preg_match($regex, $text, $match, PREG_OFFSET_CAPTURE, $position))
 		{
-			foreach ($matches[0] as $match)
-			{
-				// Replace each link with an anchor
-				$text = str_replace($match, html::anchor('http://'.$match, $match), $text);
-			}
+			list($url, $url_pos) = $match[0];
+
+			// Add the text before the url
+			$result  .= substr($text, $position, $url_pos - $position);
+
+			// Default to http://
+			$full_url = empty($match[1][0]) ? 'http://'.$url : $url;
+
+			// Add the hyperlink.
+			$result .= html::anchor($full_url, $url);
+
+			// New position to start parsing
+			$position = $url_pos + strlen($url);
 		}
 
-		return $text;
+		return $result.substr($text, $position);
 	}
 
 	/**
-- 
cgit v1.2.3