From 7c96c0574b14154762dc8d9fbb1a9ad798abcf6e Mon Sep 17 00:00:00 2001
From: mirko-pagliai <mirko.pagliai@gmail.com>
Date: Sat, 6 Jan 2024 13:10:17 +0100
Subject: [PATCH] The `BodyParser`   provides its own `urlToAbsolute()`
 protected method

---
 CHANGELOG.md               |  3 ++-
 src/Utility/BodyParser.php | 21 ++++++++++++++++++---
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 58678c0..91da21b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,7 +3,8 @@
 ### 1.1.17
 * no longer needs the me-tools package;
 * no longer uses the `Exceptionist` class;
-* provides its own `BodyParser` and `Entity` classes and no longer uses the ones provided by `php-tools`;
+* provides its own `BodyParser` and `Entity` classes and no longer uses the ones provided by `php-tools`. The `BodyParser`
+  provides its own `urlToAbsolute()` protected method;
 * ready for `php-tools` 1.8;
 * added tests for PHP 8.2.
 
diff --git a/src/Utility/BodyParser.php b/src/Utility/BodyParser.php
index 0f1909a..d21935f 100644
--- a/src/Utility/BodyParser.php
+++ b/src/Utility/BodyParser.php
@@ -14,6 +14,7 @@
  */
 namespace LinkScanner\Utility;
 
+use phpUri;
 use Symfony\Component\DomCrawler\Crawler;
 
 /**
@@ -74,6 +75,20 @@ public function __construct($body, string $url)
         $this->url = $url;
     }
 
+    /**
+     * Internal method to build an absolute url
+     * @param string $relative Relative url to join
+     * @param string $base Base path, on which to construct the absolute url
+     * @return string
+     */
+    protected function urlToAbsolute(string $relative, string $base): string
+    {
+        $base = clean_url($base, false, true);
+        $base = preg_match('/^(\w+:\/\/.+)\/[^.\/]+\.[^.\/]+$/', $base, $matches) ? $matches[1] : $base;
+
+        return phpUri::parse($base . '/')->join($relative);
+    }
+
     /**
      * Extracts links from body
      * @return array<string> Array of links
@@ -90,15 +105,15 @@ public function extractLinks(): array
 
         $crawler = new Crawler($this->body);
 
-        $links = [];
+        $extractedLinks = [];
         foreach (self::TAGS as $tag => $attribute) {
             foreach ($crawler->filterXPath('//' . $tag)->extract([$attribute]) as $link) {
                 if ($link) {
-                    $links[] = clean_url(url_to_absolute($this->url, $link), true, true);
+                    $extractedLinks[] = clean_url($this->urlToAbsolute($link, $this->url), true, true);
                 }
             }
         }
 
-        return $this->extractedLinks = array_unique($links);
+        return $this->extractedLinks = array_unique($extractedLinks);
     }
 }