Also use query and fragment when matching URIs

CHANGELOG.md

@@ -6,6 +6,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.1.2] - 2025-01-27
+### Fixed
+- When matching URIs against allow/disallow rules, the library previously used explicitly only the path part of the URI. Fixed it to use path, query and fragment.
+
 ## [1.1.1] - 2022-11-08
 ### Fixed
 - The `Parser` now also trims hidden whitespace characters that aren't covered by PHP's `trim()` function by default. Such characters at the beginning of a line can cause parsing to fail, because it's important that user-agent and rule lines actually start with the corresponding keywords.

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2024 Christian Olear
+Copyright (c) 2025 Christian Olear
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

src/RulePattern.php

@@ -25,15 +25,11 @@ public function pattern(): string
      */
     public function matches(string|Url $uri): bool
     {
-        $path = $uri instanceof Url ? $uri->path() : Url::parse($uri)->path();
+        $pathQueryFragment = $uri instanceof Url ? $uri->relative() : Url::parse($uri)->relative();
 
-        if (!is_string($path)) {
-            return false;
-        }
-
-        $path = Encoding::decodePercentEncodedAsciiCharactersInPath($path);
+        $pathQueryFragment = Encoding::decodePercentEncodedAsciiCharactersInPath($pathQueryFragment);
 
-        return preg_match($this->preparedRegexPattern(), $path) === 1;
+        return preg_match($this->preparedRegexPattern(), $pathQueryFragment) === 1;
     }
 
     private function preparedRegexPattern(): string

tests/ParserTest.php

@@ -357,6 +357,22 @@ public function test_parse_sitemap_lines(): void
         ], $robotsTxt->sitemaps());
     }
 
+    public function test_it_uses_not_only_the_path_but_also_the_query_when_matching(): void
+    {
+        $robotsTxtContent = <<<ROBOTSTXT
+            User-agent: *
+            Disallow: /?foo
+            ROBOTSTXT;
+
+        $robotsTxt = (new Parser())->parse($robotsTxtContent);
+
+        $this->assertFalse($robotsTxt->isAllowed('/?foo', 'MyBot'));
+
+        $this->assertFalse($robotsTxt->isAllowed('/?foo=bar', 'MyBot'));
+
+        $this->assertTrue($robotsTxt->isAllowed('/yo?foo=bar', 'MyBot'));
+    }
+
     /**
      * @param string[] $expected
      * @param RulePattern[] $actual