Match UAs more generously, as per google spec

So previously the UA "googlebot" would not match "googlebot-news" as the RFC says  "The robot must obey the first record in /robots.txt that contains a User-Agent line whose value contains the name token of the robot as a substring."
"googlebot-news" is not a substring of "googlebot" but the reverse is true, so we try both cases now.

Author: Tom

src/Robot/UserAgent.php

@@ -21,8 +21,8 @@ public function getMatches($userAgent)
         }
 
         $matches = array_filter($this->userAgents, function($elem) use($ua) {
-            return strpos($elem, $ua) !== false || $elem == '*';
+            return strpos($elem, $ua) !== false || strpos($ua, $elem) !== false || $elem == '*';
         });
-        return $matches;
+        return array_values($matches);
     }
 }

tests/UserAgentTest.php

@@ -93,4 +93,17 @@ public function givenWildcardAgent_alwaysMatch()
             $this->assertTrue($wildcard->getMatches($ua) == ['*'], 'wilcard matches all');
         }
     }
+
+    /**
+     * @test
+     * https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt#order-of-precedence-for-user-agents
+     */
+    public function givenGoogleExamples_behaveAsExpected()
+    {
+        $googleUAs = new UserAgent(['googlebot-news', '*', 'googlebot']);
+        $this->assertContains('googlebot-news', $googleUAs->getMatches('Googlebot-News'));
+        $this->assertContains('googlebot', $googleUAs->getMatches('Googlebot-Images'));
+        $this->assertNotContains('googlebot-news', $googleUAs->getMatches('Googlebot-Images'));
+        $this->assertEquals(['*'], $googleUAs->getMatches('otherbot'));
+    }
 }