Merge pull request #11 from nadar/relative-urls

add option for relative url check

CHANGELOG.md

@@ -3,6 +3,10 @@
 All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/).
 In order to read more about upgrading and BC breaks have a look at the [UPGRADE Document](UPGRADE.md).
 
+## 1.3.0
+
++ [#10](https://github.com/nadar/crawler/issues/10) Add relative url check to `Url` class.
+
 ## 1.2.1 (17. December 2020)
 
 + [#9](https://github.com/nadar/crawler/pull/9) Fix issue where `CRAWL_IGNORE` tag had no effect. Trim the array value for found linkes, which is equals to the link title.

src/Url.php

@@ -7,6 +7,19 @@
  *
  * In order to retrieve the url from an object use `getNormalized()`. This value is mainly used to identife and store.
  *
+ * An example where the url is checked for relative path, merge otherwise and validate:
+ * 
+ * ```php
+ * $url = new Url('/about/me');
+ * if ($url->isRelative()) {
+ *     $url->merge(new Url('https://luya.io'));
+ * }
+ * 
+ * if ($url->isValid()) {
+ *     echo $url->getNormalized(); // outputs https://luya.io/about/me
+ * }
+ * ```
+ * 
  * @author Basil Suter <[email protected]>
  * @since 1.0.0
  */
@@ -150,6 +163,17 @@ public function isValid()
     {
         return !in_array($this->getScheme(), ['mailto', 'tel', 'ftp']);
     }
+
+    /**
+     * Whether the original url is a relative url or not
+     *
+     * @return boolean
+     * @since 1.3.0
+     */
+    public function isRelative()
+    {
+        return strncmp($this->url, '//', 2) && strpos($this->url, '://') === false;
+    }
 
     /**
      * If the current URL is missing informations, it cain obtain informations from the to merge url

tests/UrlTest.php

@@ -74,4 +74,13 @@ public function testInvalidUrl()
         $this->assertTrue((new Url('https://luya.io'))->isValid());
         $this->assertTrue((new Url('/admin/path'))->isValid());
     }
+
+    public function testIsRelative()
+    {
+        $this->assertFalse((new Url('https://luya.io'))->isRelative());
+        $this->assertFalse((new Url('https://luya.io/path//double'))->isRelative());
+        $this->assertFalse((new Url('//path-without-host'))->isRelative());
+        $this->assertTrue((new Url('/path-without-host'))->isRelative());
+        $this->assertTrue((new Url('path-without-host/base-path-info-required'))->isRelative());
+    }
 }