Merge pull request #1 from aternosorg/invalid-encoding

Fix fatal error that is thrown when the input string has an invalid encoding

Author: JulianVennen

composer.json

@@ -1,34 +1,37 @@
 {
     "name": "aternos/licensee",
     "description": "A library to detect well-known licenses based on their title or content.",
-    "type": "library",
     "license": "MIT",
-    "bin": ["bin/licensee-update-data"],
-    "autoload": {
-        "psr-4": {
-            "Aternos\\Licensee\\": "src/"
-        }
-    },
-    "autoload-dev": {
-        "psr-4": {
-            "Tests\\": "tests/"
-        }
-    },
+    "type": "library",
     "authors": [
         {
             "name": "Kurt Thiemann",
             "email": "[email protected]"
         }
     ],
     "require": {
+        "php": ">=8.3",
         "ext-dom": "*",
-        "league/html-to-markdown": "^5.1",
+        "ext-mbstring": "*",
         "ext-yaml": "*",
-        "php": ">=8.3"
+        "league/html-to-markdown": "^5.1"
     },
     "require-dev": {
         "phpunit/phpunit": "^11.5"
     },
+    "autoload": {
+        "psr-4": {
+            "Aternos\\Licensee\\": "src/"
+        }
+    },
+    "autoload-dev": {
+        "psr-4": {
+            "Tests\\": "tests/"
+        }
+    },
+    "bin": [
+        "bin/licensee-update-data"
+    ],
     "scripts": {
         "test": "phpunit --config phpunit.xml --testdox"
     }

composer.lock

@@ -33,9 +33,13 @@
 use Aternos\Licensee\TextTransformer\StripUrlTransformer;
 use Aternos\Licensee\TextTransformer\StripVersionTransformer;
 use Aternos\Licensee\TextTransformer\StripWhitespaceTransformer;
+use Aternos\Licensee\TextTransformer\TextTransformer;
 
 class LicenseText
 {
+    /**
+     * @var TextTransformer[]
+     */
     protected array $transformers;
     protected ?string $normalizedContent = null;
     protected ?array $wordSet = null;
@@ -101,7 +105,7 @@ public function __construct(
     public function getNormalizedContent(): string
     {
         if ($this->normalizedContent === null) {
-            $this->normalizedContent = $this->content;
+            $this->normalizedContent = mb_convert_encoding($this->content, 'utf8');
             foreach ($this->transformers as $transformer) {
                 $this->normalizedContent = $transformer->transform($this->normalizedContent);
                 $this->normalizedContent = RegExpException::handleNull(preg_replace("# +#", " ", $this->normalizedContent));