From 759eb5f76e079022dc3342181d500e72285ee978 Mon Sep 17 00:00:00 2001
From: Barnaby Walters <barnaby@waterpigs.co.uk>
Date: Thu, 17 Jan 2013 20:21:14 +0000
Subject: [PATCH] Added HTML test for findUrls()

---
 BarnabyWalters/Helpers/Helpers.php           | 13 +++++++------
 tests/BarnabyWalters/Helpers/HelpersTest.php | 13 ++++++++++++-
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/BarnabyWalters/Helpers/Helpers.php b/BarnabyWalters/Helpers/Helpers.php
index 305f38e..fa3175a 100644
--- a/BarnabyWalters/Helpers/Helpers.php
+++ b/BarnabyWalters/Helpers/Helpers.php
@@ -461,20 +461,21 @@ public static function atomDate($date) {
      * @return array An array containing all the URLs found in $text
      */
     public static function findUrls($text, $tidy = true) {
-        // Pattern is from 1 cassis.js, slightly modified to not look for twitter names
-        // E.G. beforehand it would return @tantek for @tantek.com. This function is just interested in addresses, not twitter stuff
-        $pattern = '/(?:(?:(?:(?:http|https|irc)?:\\/\\/(?:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+(?:\\:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+)?\\@)?)?(?:(?:(?:[a-zA-Z0-9][-a-zA-Z0-9]*\\.)+(?:(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])|(?:biz|b[abdefghijmnorstvwyz])|(?:cat|com|coop|c[acdfghiklmnoruvxyz])|d[ejkmoz]|(?:edu|e[cegrstu])|f[ijkmor]|(?:gov|g[abdefghilmnpqrstuwy])|h[kmnrtu]|(?:info|int|i[delmnoqrst])|j[emop]|k[eghimnrwyz]|l[abcikrstuvy]|(?:mil|museum|m[acdeghklmnopqrstuvwxyz])|(?:name|net|n[acefgilopruz])|(?:org|om)|(?:pro|p[aefghklmnrstwy])|qa|r[eouw]|s[abcdeghijklmnortuvyz]|(?:tel|travel|t[cdfghjklmnoprtvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[etu]|z[amw]))|(?:(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])))(?:\\:\\d{1,5})?)(?:\\/(?:(?:[!#&-;=?-Z_a-z~])|(?:\\%[a-fA-F0-9]{2}))*)?)(?=\\b|\\s|$)/';
+        // Pattern is from 1 cassis.js, slightly modified to not look for 
+        // twitter names E.G. beforehand it would return @tantek for @tantek.com.
+        // This function is just interested in addresses, not twitter stuff
+        $pattern = '/(?:(?:(?:(?:http|https|irc)?:\\/\\/(?:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+(?:\\:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+)?\\@)?)?(?:(?:(?:[a-zA-Z0-9][-a-zA-Z0-9]*\\.)+(?:(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])|(?:biz|b[abdefghijmnorstvwyz])|(?:cat|com|coop|c[acdfghiklmnoruvxyz])|d[ejkmoz]|(?:edu|e[cegrstu])|f[ijkmor]|(?:gov|g[abdefghilmnpqrstuwy])|h[kmnrtu]|(?:info|int|i[delmnoqrst])|j[emop]|k[eghimnrwyz]|l[abcikrstuvy]|(?:mil|museum|m[acdeghklmnopqrstuvwxyz])|(?:name|net|n[acefgilopruz])|(?:org|om)|(?:pro|p[aefghklmnrstwy])|qa|r[eouw]|s[abcdeghijklmnortuvyz]|(?:tel|travel|t[cdfghjklmnoprtvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[etu]|z[amw]))|(?:(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])))(?:\\:\\d{1,5})?)(?:\\/(?:(?:[!#&-;=?-Z_a-z~])|(?:\\%[a-fA-F0-9]{2}))*)?)(?=\\b|\\s|$)/i';
 
         $c = preg_match_all($pattern, $text, $m);
 
-        if ($c) {
+        if ($c !== false) {
             // Normalise
             $links = array_values($m[0]);
 
             ob_start();
             $links = array_map(function($value) use ($tidy) {
-                        return $tidy ? \web_address_to_uri($value, true) : $value;
-                    }, $links);
+                    return $tidy ? \web_address_to_uri($value, true) : $value;
+                }, $links);
             ob_end_clean();
 
             // $links = ['http://someurl.tld', •••]
diff --git a/tests/BarnabyWalters/Helpers/HelpersTest.php b/tests/BarnabyWalters/Helpers/HelpersTest.php
index 14edc33..51079a4 100644
--- a/tests/BarnabyWalters/Helpers/HelpersTest.php
+++ b/tests/BarnabyWalters/Helpers/HelpersTest.php
@@ -279,11 +279,22 @@ public function testAtomDate() {
      * @group text
      * @group helpers
      */
-    public function testFindURLs() {
+    public function testFindUrlsFindsUrlsInPlaintext() {
         $testString = 'Okay, so this string contains some URLs. http://waterpigs.co.uk, identi.ca, aaron.pk';
         $testArray = array('http://waterpigs.co.uk', 'http://identi.ca', 'http://aaron.pk');
+        
         $this->assertEquals($testArray, H::findUrls($testString));
     }
+    
+    public function testFindUrlsFindsUrlsInAHref() {
+        $html = '<div class="p-name entry-title p-summary summary e-content entry-content">
+            <p>T5 <a rel="tag" href="/tags/pingback">#pingback</a> mentioning <a href="http://localhost.com/notes/711/">another note</a> <a rel="tag" href="/tags/test">#test</a> <a rel="tag" href="/tags/notweet">#notweet</a></p>
+        </div>';
+        $expected = ['http://localhost.com/notes/711'];
+        $result = H::findUrls($html);
+        
+        $this->assertEquals($expected, $result);
+    }
 
 }